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

    Neuronpedia

    INDEX
    Explanations

    comparison operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enie
    0.38
    )/\
    0.37
    asius
    0.36
    alach
    0.36
    狼
    0.36
    pasar
    0.35
    電機
    0.35
     доме
    0.35
    ich
    0.35
    €
    0.34
    POSITIVE LOGITS
     ANYTHING
    0.41
    Anything
    0.41
     anything
    0.40
    anything
    0.38
     Anything
    0.37
     clipart
    0.35
     trivia
    0.35
    Tìm
    0.35
    的首
    0.34
     Bold
    0.34
    Act Density 0.056%

    No Known Activations