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

    Neuronpedia

    INDEX
    Explanations

    intelligence and knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tables
    -0.08
     Celt
    -0.07
    .top
    -0.07
     Browns
    -0.06
     shark
    -0.06
    lardır
    -0.06
     window
    -0.06
    ador
    -0.06
    ид
    -0.06
     uw
    -0.06
    POSITIVE LOGITS
     Nobody
    0.07
     Fundamental
    0.06
    생님
    0.06
     Association
    0.06
     logits
    0.06
    เกษ
    0.06
     legislation
    0.06
    _FINISH
    0.06
    .ResponseWriter
    0.06
    ˆ
    0.06
    Act Density 0.019%

    No Known Activations