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

    Neuronpedia

    INDEX
    Explanations

    * per se

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    0.80
    の間
    0.79
    لي
    0.77
    präsident
    0.75
    اً
    0.75
    야
    0.74
    t
    0.73
    tgt
    0.73
    ará
    0.72
    א
    0.72
    POSITIVE LOGITS
    0.84
    ,
    0.82
     equestrian
    0.75
     gyn
    0.73
    \}
    0.72
    ak
    0.71
     neuromuscular
    0.69
     sprinter
    0.66
     literary
    0.66
     wry
    0.66
    Act Density 0.001%

    No Known Activations