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

    Neuronpedia

    INDEX
    Explanations

    recognizing pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouncer
    0.46
    ório
    0.44
     Endocrinol
    0.43
    ceu
    0.43
     Deliver
    0.43
    ympt
    0.42
     Orthodox
    0.42
    jer
    0.41
    uken
    0.40
    ivalent
    0.40
    POSITIVE LOGITS
    图案
    0.48
     PARTY
    0.45
     ENGINEERING
    0.44
     точку
    0.42
    郅
    0.42
    闥
    0.40
    ૃહ
    0.40
    櫸
    0.40
     पैटर्न
    0.40
    πτωση
    0.40
    Act Density 0.003%

    No Known Activations