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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens that are multiples of three.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    科
    -0.06
    ia
    -0.06
    _GEN
    -0.06
    ium
    -0.06
     Herb
    -0.06
     gap
    -0.06
     Erin
    -0.06
    WA
    -0.06
     section
    -0.06
     Permit
    -0.06
    POSITIVE LOGITS
    108
    0.09
    252
    0.09
    12
    0.08
    移動
    0.08
    288
    0.08
    360
    0.08
    Taylor
    0.08
    ancellor
    0.08
    72
    0.08
    ตอบ
    0.08
    Act Density 0.410%

    No Known Activations