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

    Neuronpedia

    INDEX
    Explanations

    full/filled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     residual
    -0.07
    (depend
    -0.06
     دید
    -0.06
    _profit
    -0.06
     Jensen
    -0.06
     Labels
    -0.06
    licos
    -0.06
     LOVE
    -0.06
    shortcode
    -0.06
    opoly
    -0.06
    POSITIVE LOGITS
     �
    0.07
    -Apr
    0.06
     Р
    0.06
    Wrapped
    0.06
    жно
    0.06
    �
    0.06
    Australia
    0.06
     strive
    0.06
    TITLE
    0.06
    Tonight
    0.06
    Act Density 0.036%

    No Known Activations