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

    Neuronpedia

    INDEX
    Explanations

    sock

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �果
    -0.07
    ��加
    -0.07
    adaptive
    -0.07
    =""></
    -0.07
    ธน
    -0.06
    ***/↵
    -0.06
    超过
    -0.06
    FFFFFFFF
    -0.06
    後
    -0.06
    _Address
    -0.06
    POSITIVE LOGITS
    alama
    0.07
     Cavaliers
    0.07
     Axios
    0.07
    ToF
    0.06
     tooltip
    0.06
    /list
    0.06
    ヾ
    0.06
    lenme
    0.06
     cudd
    0.06
    ajan
    0.06
    Act Density 0.377%

    No Known Activations