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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .activity
    -0.07
     Adoles
    -0.07
     Prest
    -0.07
     уров
    -0.06
     EVER
    -0.06
    也
    -0.06
     emotion
    -0.06
    -foot
    -0.06
    ácil
    -0.06
     yans
    -0.06
    POSITIVE LOGITS
    Copying
    0.07
     restitution
    0.07
     Cumhurbaşkanı
    0.06
    dar
    0.06
    builder
    0.06
    arn
    0.06
    74
    0.06
    Conexion
    0.06
    .reloadData
    0.06
    Minnesota
    0.06
    Act Density 0.000%

    No Known Activations