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

    Neuronpedia

    INDEX
    Explanations

    return to original life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тор
    0.54
    ème
    0.50
    entrée
    0.50
    סי
    0.49
    a
    0.49
    ה
    0.49
    ך
    0.49
    া
    0.48
     setembro
    0.47
    се
    0.47
    POSITIVE LOGITS
     /{
    0.52
     उन्‍ह
    0.47
     ={
    0.46
    羚
    0.44
    短暂
    0.44
     Lough
    0.43
     Gü
    0.42
     Gallows
    0.42
     ⏮
    0.41
    breviations
    0.41
    Act Density 0.000%

    No Known Activations