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

    Neuronpedia

    INDEX
    Explanations

    activism/social issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.99
    LookAnd
    -0.95
    :✨
    -0.92
    GEBURTSDATUM
    -0.91
    featureID
    -0.91
     للاسماء
    -0.89
    principalColumn
    -0.89
    CloseOperation
    -0.83
    IsMutable
    -0.82
    Personendaten
    -0.80
    POSITIVE LOGITS
    ప
    0.52
    reno
    0.49
    break
    0.49
    利
    0.49
    co
    0.49
     concerned
    0.48
    pager
    0.47
    en
    0.46
    付
    0.46
    Te
    0.45
    Act Density 0.139%

    No Known Activations