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

    Neuronpedia

    INDEX
    Explanations

    '5' followed by '6'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ক্রিয়া
    0.39
    渲
    0.34
    യും
    0.32
    =".
    0.32
     adaptador
    0.32
    incinnati
    0.32
     मददगार
    0.32
     tribunals
    0.32
    ซิต
    0.32
     erreurs
    0.31
    POSITIVE LOGITS
    fabricated
    0.33
    ती
    0.32
     corroborated
    0.31
     Qualified
    0.30
    padded
    0.29
    here
    0.29
     тут
    0.29
     compromised
    0.29
    сят
    0.29
     счита
    0.29
    Act Density 0.004%

    No Known Activations