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

    Neuronpedia

    INDEX
    Explanations

    list item marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دارة
    1.09
    صال
    1.03
     તા
    1.02
     lanjutan
    1.01
    你有
    0.99
     rolling
    0.98
    nın
    0.97
    ண்டும்
    0.97
    न
    0.96
    ítható
    0.96
    POSITIVE LOGITS
    Defendants
    1.48
    푸
    1.40
    as
    1.39
    ़
    1.36
    FBSDKInternal
    1.33
    ᅳ
    1.32
    peach
    1.30
    arabic
    1.30
    োই
    1.28
    ं
    1.27
    Act Density 0.541%

    No Known Activations