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

    Neuronpedia

    INDEX
    Explanations

    Code initialization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getConfig
    -0.07
    Miller
    -0.07
    ぷ
    -0.07
    uren
    -0.07
     Hunter
    -0.07
     mogelijk
    -0.06
     לפתוח
    -0.06
    层出不穷
    -0.06
     Mueller
    -0.06
    本期
    -0.06
    POSITIVE LOGITS
    индив
    0.07
     sociology
    0.07
    istry
    0.06
    挂在
    0.06
    LocalizedMessage
    0.06
     realms
    0.06
     (...)
    0.06
    _restrict
    0.06
    Ā
    0.06
    程式
    0.06
    Act Density 0.127%

    No Known Activations