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

    Neuronpedia

    INDEX
    Explanations

    mathematics and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cry
    -0.06
     gunshot
    -0.06
     Investing
    -0.06
    ioned
    -0.06
     دوب
    -0.06
    .iv
    -0.06
     Lowest
    -0.06
     Kremlin
    -0.06
     hayal
    -0.06
     кирп
    -0.06
    POSITIVE LOGITS
     parser
    0.07
    instagram
    0.07
    eating
    0.07
     necessary
    0.06
    _residual
    0.06
    peat
    0.06
    ])-
    0.06
    ...
    0.06
    PathParam
    0.06
    subscription
    0.06
    Act Density 0.013%

    No Known Activations