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

    Neuronpedia

    INDEX
    Explanations

    say "ower"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ex
    -0.08
    تقلي
    -0.07
    _blue
    -0.07
    ?!↵↵
    -0.06
    샴
    -0.06
    Associ
    -0.06
    люб
    -0.06
     Mini
    -0.06
     Remain
    -0.06
    .vis
    -0.06
    POSITIVE LOGITS
    RC
    0.08
    RV
    0.07
    埗
    0.07
    &T
    0.07
     rm
    0.07
     الهيئة
    0.07
    neas
    0.07
     rob
    0.07
    Land
    0.07
    悸
    0.07
    Act Density 0.009%

    No Known Activations