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

    Neuronpedia

    INDEX
    Explanations

    articles often, very large

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ンプル
    0.45
    ichtigung
    0.41
    ply
    0.40
    øg
    0.40
    iencing
    0.40
    ピア
    0.39
    看完
    0.39
    jö
    0.39
     পারছি
    0.39
     पश्चिम
    0.39
    POSITIVE LOGITS
    હા
    0.40
     Huguen
    0.39
     Buenas
    0.38
     قاعد
    0.37
     refinance
    0.37
    updateOne
    0.36
    &&\
    0.35
     ESA
    0.35
     MAPE
    0.35
     Zeke
    0.35
    Act Density 0.020%

    No Known Activations