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

    Neuronpedia

    INDEX
    Explanations

    To kill a mockingbird

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Means
    0.46
     means
    0.45
     "|"
    0.40
    สูง
    0.40
     MEANS
    0.39
    Means
    0.39
    means
    0.38
    󠁿
    0.37
    잘
    0.37
     moneys
    0.36
    POSITIVE LOGITS
    ledo
    0.46
    To
    0.41
     paraphrase
    0.39
    ffee
    0.38
    чнее
    0.38
    ଟି
    0.38
    Tob
    0.38
    Toc
    0.38
     avoid
    0.37
     Whom
    0.37
    Act Density 0.007%

    No Known Activations