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

    Neuronpedia

    INDEX
    Explanations

    singles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Doug
    -0.07
    _rule
    -0.06
     villa
    -0.06
    ка
    -0.06
     朝
    -0.06
    Bah
    -0.06
     Bon
    -0.06
     allergy
    -0.06
    daily
    -0.06
     आदम
    -0.06
    POSITIVE LOGITS
    .Sequential
    0.07
     فوق
    0.07
    clas
    0.06
     Staples
    0.06
    'name
    0.06
    (Sender
    0.06
    )size
    0.06
    ouve
    0.06
    _bloc
    0.06
    igsaw
    0.06
    Act Density 0.002%

    No Known Activations