Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    individuals associated with professional achievements or recognition in specific fields.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects numeric date tokens—especially years (e.g. “2012,” “2013,” “2019”)—often in “As of” or date‐declaration contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gun
    -0.07
     Chevrolet
    -0.06
    roc
    -0.06
     Cs
    -0.06
     panor
    -0.06
     warm
    -0.06
     mir
    -0.06
     Něk
    -0.06
    алом
    -0.06
     城
    -0.06
    POSITIVE LOGITS
     ValidationResult
    0.06
     unconstitutional
    0.06
     acuerdo
    0.06
    ;">↵
    0.06
     formulate
    0.06
     ///
    0.06
     همچنین
    0.06
     decals
    0.06
     spaced
    0.06
    .AddScoped
    0.06
    Act Density 0.012%

    No Known Activations