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

    Neuronpedia

    INDEX
    Explanations

    divide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ádu
    -0.07
    �数
    -0.07
     giàu
    -0.07
    ाह
    -0.07
    resp
    -0.07
     ot
    -0.07
     Sof
    -0.06
    _notifications
    -0.06
     наст
    -0.06
     referencia
    -0.06
    POSITIVE LOGITS
     Clara
    0.07
    Neutral
    0.07
     сті
    0.07
    ?]
    0.07
    "k
    0.06
     Bison
    0.06
    ucking
    0.06
    (binding
    0.06
    (commit
    0.06
    ってい
    0.06
    Act Density 0.001%

    No Known Activations