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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ging
    -0.07
     disciplinary
    -0.07
     accusing
    -0.07
    أستاذ
    -0.07
     ascend
    -0.06
    叩
    -0.06
    Menus
    -0.06
    asse
    -0.06
    PIP
    -0.06
    赇
    -0.06
    POSITIVE LOGITS
    WT
    0.07
    _margin
    0.07
     aggregate
    0.06
    ват
    0.06
    ByKey
    0.06
    ברה
    0.06
    -query
    0.06
    Ｎ
    0.06
    沓
    0.06
    .fromString
    0.06
    Act Density 0.018%

    No Known Activations