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

    Neuronpedia

    INDEX
    Explanations

    ~

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spanking
    -0.07
    metric
    -0.06
     культуры
    -0.06
    ummies
    -0.06
    вали
    -0.06
    ěti
    -0.06
    UNCT
    -0.06
    ()',
    -0.06
    thumb
    -0.06
    agas
    -0.06
    POSITIVE LOGITS
     할
    0.06
    Salir
    0.06
     徒
    0.06
     напря
    0.06
     productions
    0.06
    .↵↵↵↵
    0.06
    lox
    0.06
    Під
    0.06
     onPostExecute
    0.06
    _loaded
    0.06
    Act Density 0.020%

    No Known Activations