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

    Neuronpedia

    INDEX
    Explanations

    remote jobs, lawyers, crisis text, ML flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    charset
    0.27
    ೆಯಿಂದ
    0.26
     deleterious
    0.25
    physiological
    0.25
    composition
    0.25
     cytoskeleton
    0.23
    るので
    0.23
     بابەت
    0.22
    define
    0.22
    ಾದರೂ
    0.22
    POSITIVE LOGITS
    ica
    0.28
    -
    0.28
    كس
    0.28
    ट
    0.27
    aholic
    0.27
    у
    0.26
    ট
    0.26
    x
    0.26
    бе
    0.25
    +,
    0.25
    Act Density 0.293%

    No Known Activations