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

    Neuronpedia

    INDEX
    Explanations

    "sucks" or "suck"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    1.43
    f
    1.38
    h
    1.37
    ین
    1.32
    y
    1.30
    ，
    1.30
    ี
    1.28
    ോ
    1.28
    é
    1.26
    ד
    1.22
    POSITIVE LOGITS
    𝗮
    1.25
    ujjati
    1.23
     daarbij
    1.21
     tempHeader
    1.20
    그러나
    1.20
     bahawa
    1.18
    ą
    1.18
    ^{*}$-
    1.17
     এতে
    1.15
    𝗴
    1.15
    Act Density 0.000%

    No Known Activations