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

    Neuronpedia

    INDEX
    Explanations

    Book reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Emotional
    -0.10
    Chan
    -0.07
    slope
    -0.07
     flames
    -0.07
    (obj
    -0.07
    温
    -0.07
    解
    -0.06
    _lin
    -0.06
    [id
    -0.06
    _on
    -0.06
    POSITIVE LOGITS
    𬍡
    0.07
    .KeyPress
    0.07
    localized
    0.07
     meny
    0.07
     bugün
    0.07
     LESS
    0.07
    producer
    0.07
    _written
    0.06
    少许
    0.06
     YYSTACK
    0.06
    Act Density 0.051%

    No Known Activations