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

    Neuronpedia

    INDEX
    Explanations

    anonymous person or source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.65
    ية
    0.63
    ।’
    0.63
     iPhones
    0.57
     it
    0.57
    p
    0.57
    ↵↵
    0.57
    ’।
    0.57
    ।
    0.56
    ty
    0.56
    POSITIVE LOGITS
    at
    0.86
    ET
    0.71
    OS
    0.68
    em
    0.66
    AT
    0.66
    AN
    0.66
    á
    0.64
    AIN
    0.64
    is
    0.61
    il
    0.61
    Act Density 0.002%

    No Known Activations