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

    Neuronpedia

    INDEX
    Explanations

    quotes, Assembly, game, years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     konfl
    0.46
    <unused28>
    0.46
    conversion
    0.45
     conversion
    0.43
    }|^{
    0.41
    **.
    0.40
     एपिस
    0.40
    <unused48>
    0.39
    匱
    0.39
     financi
    0.39
    POSITIVE LOGITS
     Shel
    0.43
    Bracket
    0.40
    耍
    0.39
     Joel
    0.38
    Yo
    0.37
    Pav
    0.37
     Gl
    0.37
     Yo
    0.36
     pickup
    0.36
    Shel
    0.36
    Act Density 0.000%

    No Known Activations