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

    Neuronpedia

    INDEX
    Explanations

    code, function definitions, and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    માં
    1.95
    r
    1.86
    トート
    1.75
    ل
    1.74
    таю
    1.73
    ות
    1.67
    stion
    1.66
    ية
    1.64
     EHR
    1.63
    čia
    1.63
    POSITIVE LOGITS
    gomery
    1.50
    ுள்ளது
    1.48
     Saltar
    1.38
    𝘰
    1.34
    𝘢
    1.33
    ্ব
    1.31
    ي
    1.31
    𝚑
    1.28
    𝘶
    1.27
     einzigen
    1.25
    Act Density 0.051%

    No Known Activations