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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     налог
    -0.08
    зор
    -0.08
     Enough
    -0.08
     العالي
    -0.08
     clan
    -0.08
    adakan
    -0.08
     قابلیت
    -0.08
    ుడ
    -0.07
     сюжет
    -0.07
     Taj
    -0.07
    POSITIVE LOGITS
     עבור
    0.09
    fen
    0.08
     Janeiro
    0.08
    趋
    0.08
     অনুয
    0.08
    和值
    0.07
     concernant
    0.07
     described
    0.07
    .Append
    0.07
     Cd
    0.07
    Act Density 0.005%

    No Known Activations