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

    Neuronpedia

    INDEX
    Explanations

    asking to name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ला
    0.54
    کر
    0.50
    اد
    0.45
     around
    0.42
    نا
    0.41
     specialists
    0.40
    کت
    0.40
    ри
    0.39
     wording
    0.39
    นี้
    0.39
    POSITIVE LOGITS
     nascimento
    0.49
    born
    0.47
     ধরনের
    0.47
    unna
    0.46
     Nei
    0.46
     формы
    0.46
     іх
    0.46
     Marlene
    0.46
     Morrissey
    0.46
     مواليد
    0.45
    Act Density 0.006%

    No Known Activations