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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects references to formal organizations or regulatory/professional bodies (e.g., agency or society names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    medical and safety-related terminology in the context of chemical substances.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    FD
    -0.06
    []>(
    -0.06
    ुभ
    -0.06
     Bil
    -0.06
     pillow
    -0.06
    .blog
    -0.06
    memcmp
    -0.06
     HTC
    -0.06
    终
    -0.06
    (DIS
    -0.06
    POSITIVE LOGITS
    (gr
    0.07
    	parameters
    0.07
     Tale
    0.07
    SECOND
    0.07
    -lines
    0.06
    ffi
    0.06
    lerinin
    0.06
    viron
    0.06
    ------↵↵
    0.06
    (article
    0.06
    Act Density 0.057%

    No Known Activations