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

    Neuronpedia

    INDEX
    Explanations

    worker walks into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appunto
    0.36
     indol
    0.35
     hapless
    0.34
     sullen
    0.33
     capricious
    0.31
     interplay
    0.31
    ؛
    0.30
     sleek
    0.30
     genus
    0.29
     recombin
    0.29
    POSITIVE LOGITS
    on
    0.40
    а
    0.38
    今天
    0.37
    这个
    0.36
    pessoas
    0.35
    वाधिकार
    0.35
    昨天
    0.34
    ai
    0.33
     окружающей
    0.33
    拉
    0.33
    Act Density 0.318%

    No Known Activations