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

    Neuronpedia

    INDEX
    Explanations

    discriminant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .learn
    -0.07
     �
    -0.07
    cba
    -0.07
    uter
    -0.07
     آذ
    -0.06
     河
    -0.06
    (stock
    -0.06
    .lazy
    -0.06
     Mell
    -0.06
    .focus
    -0.06
    POSITIVE LOGITS
    SEL
    0.07
    upro
    0.06
    django
    0.06
    _nm
    0.06
     Installed
    0.06
    201
    0.06
     Ago
    0.06
    privacy
    0.06
     knowingly
    0.06
    "io
    0.06
    Act Density 0.002%

    No Known Activations