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

    Neuronpedia

    INDEX
    Explanations

    multi-column layouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.65
     finite
    0.59
    Matter
    0.59
     number
    0.59
     unique
    0.58
     특별
    0.57
     subset
    0.57
     digital
    0.57
     special
    0.56
     collection
    0.55
    POSITIVE LOGITS
    ה
    0.84
    က
    0.67
    νες
    0.67
    በረ
    0.64
    сли
    0.64
    י
    0.64
    ಮ
    0.63
    كار
    0.63
    τι
    0.62
    ص
    0.62
    Act Density 0.000%

    No Known Activations