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

    Neuronpedia

    INDEX
    Explanations

    any of decisions or harmful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Some
    0.60
     It
    0.60
     I
    0.59
    íss
    0.59
    '।
    0.56
    ’
    0.56
     Needed
    0.55
    。
    0.55
     SOME
    0.55
    ’।
    0.54
    POSITIVE LOGITS
    ס
    0.70
    ור
    0.66
    든지
    0.64
    THING
    0.61
     of
    0.57
     новую
    0.55
    ד
    0.55
     parecido
    0.53
    of
    0.52
    were
    0.52
    Act Density 0.067%

    No Known Activations