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

    Neuronpedia

    INDEX
    Explanations

    descriptions with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ні
    0.53
    мін
    0.46
     Reflections
    0.45
    ية
    0.44
    К
    0.42
     समर्
    0.41
    ци
    0.41
     reflections
    0.41
     Uniti
    0.41
    Ло
    0.41
    POSITIVE LOGITS
     prix
    0.47
     श्रृंखला
    0.47
     обеспе
    0.46
    JN
    0.46
     corrupción
    0.43
     जोश
    0.41
     batería
    0.41
     пыта
    0.39
    yas
    0.39
     educación
    0.39
    Act Density 0.001%

    No Known Activations