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

    Neuronpedia

    INDEX
    Explanations

    sure to elicit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Locale
    0.60
     Appleton
    0.58
     الجذر
    0.58
     Basis
    0.58
     প্রতিদিনই
    0.57
     giả
    0.57
    არ
    0.57
     Mastery
    0.56
     NotFound
    0.55
     unapolog
    0.55
    POSITIVE LOGITS
    ي
    0.74
    </h3>
    0.70
    -
    0.70
    is
    0.66
    els
    0.66
    ۳
    0.66
    es
    0.62
     ی
    0.62
    จะ
    0.61
    osomes
    0.61
    Act Density 0.000%

    No Known Activations