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

    Neuronpedia

    INDEX
    Explanations

    code/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bruises
    -0.07
    (rgb
    -0.07
    rients
    -0.07
     geld
    -0.06
    gis
    -0.06
    视察
    -0.06
     Celtic
    -0.06
     gee
    -0.06
    rtle
    -0.06
     Strikes
    -0.06
    POSITIVE LOGITS
    .menu
    0.07
    🚔
    0.07
    _pending
    0.07
    Fecha
    0.07
     graduates
    0.07
    棤
    0.07
    Tabla
    0.07
    전
    0.06
    أسر
    0.06
    Ac
    0.06
    Act Density 0.594%

    No Known Activations