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

    Neuronpedia

    INDEX
    Explanations

    formula components in definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neden
    0.52
     kenapa
    0.47
     analisi
    0.44
     análise
    0.41
     why
    0.40
     WHY
    0.40
     analisis
    0.40
    কাঠ
    0.40
     وجہ
    0.40
    为什么
    0.40
    POSITIVE LOGITS
     Donde
    0.59
     Where
    0.54
     where
    0.54
     где
    0.54
     όπου
    0.54
     حيث
    0.52
     其中
    0.52
     let
    0.52
    where
    0.51
     donde
    0.51
    Act Density 0.003%

    No Known Activations