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

    Neuronpedia

    INDEX
    Explanations

    recorded, patched, paying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Edwin
    0.46
    Сейчас
    0.46
    Metro
    0.45
    Couple
    0.45
     Sosial
    0.43
    㑼
    0.43
    pleo
    0.43
    푐
    0.43
     الناس
    0.42
     waahanga
    0.42
    POSITIVE LOGITS
    raise
    0.46
     bank
    0.45
    ext
    0.44
     inadequate
    0.43
     require
    0.43
     raises
    0.43
     naive
    0.43
    na
    0.42
     posts
    0.42
    enz
    0.41
    Act Density 0.389%

    No Known Activations