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

    Neuronpedia

    INDEX
    Explanations

    issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.34
    ность
    0.34
    ’
    0.32
    ール
    0.32
     funcione
    0.32
     manière
    0.31
    。
    0.31
     regole
    0.31
    графии
    0.30
     spéciale
    0.30
    POSITIVE LOGITS
    ang
    0.41
     مع
    0.37
     burning
    0.37
    até
    0.36
     बीमारियों
    0.35
     poisoning
    0.34
    unlist
    0.34
     आरोग
    0.33
     cystic
    0.33
    adau
    0.33
    Act Density 0.000%

    No Known Activations