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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Declared
    -0.06
    ้อ
    -0.06
    осуд
    -0.06
     Vs
    -0.06
    .DataSource
    -0.06
     beliefs
    -0.06
    /licenses
    -0.06
    jspb
    -0.06
     mối
    -0.06
     Mayor
    -0.05
    POSITIVE LOGITS
    太阳城
    0.07
    ajaran
    0.07
     addItem
    0.07
    介
    0.07
    unma
    0.06
    lamış
    0.06
    _access
    0.06
     siguiente
    0.06
    戦
    0.06
    abeth
    0.06
    Act Density 0.030%

    No Known Activations