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

    Neuronpedia

    INDEX
    Explanations

    formulas and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.61
    //!
    0.59
    t
    0.58
    W
    0.57
    retry
    0.52
     They
    0.50
    us
    0.50
    IENT
    0.47
    ก
    0.47
     Transforming
    0.46
    POSITIVE LOGITS
     on
    0.69
     at
    0.67
    كل
    0.59
    2
    0.59
    ﺎ
    0.59
    τη
    0.57
    த்தை
    0.57
     οποίο
    0.57
     соответству
    0.56
     такую
    0.55
    Act Density 0.000%

    No Known Activations