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

    Neuronpedia

    INDEX
    Explanations

    in other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Other
    0.44
     JULY
    0.42
    tenths
    0.41
    题
    0.41
     lspace
    0.40
     Domb
    0.40
     Otros
    0.39
     tain
    0.37
     ಹೊ
    0.37
    Otros
    0.37
    POSITIVE LOGITS
     variable
    0.49
     variabili
    0.47
     перемен
    0.46
     variabile
    0.43
     variables
    0.42
     variável
    0.42
    变量
    0.42
     değişken
    0.42
    Variable
    0.40
    行動
    0.40
    Act Density 0.010%

    No Known Activations