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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially decimal numbers and ratings—highlighting measurements or metrics in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uch
    -0.06
    kou
    -0.06
     giảng
    -0.06
    onz
    -0.06
    <div
    -0.06
    .POS
    -0.06
     exped
    -0.06
    )});↵
    -0.06
    Christopher
    -0.06
    }");↵
    -0.06
    POSITIVE LOGITS
    ตรว
    0.07
    μές
    0.06
    _Length
    0.06
     παν
    0.06
     Crowley
    0.06
     超
    0.06
    에는
    0.06
    iley
    0.06
     �
    0.06
     outright
    0.06
    Act Density 0.055%

    No Known Activations