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

    Neuronpedia

    INDEX
    Explanations

    vibe check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.61
    an
    0.55
    ä
    0.52
    ie
    0.50
    ae
    0.49
    ade
    0.46
    made
    0.46
    ir
    0.45
    ok
    0.45
    uc
    0.45
    POSITIVE LOGITS
     ощущение
    0.57
     sensação
    0.57
     Gefühl
    0.48
    的感觉
    0.48
    OfDeath
    0.48
    邡
    0.47
     분위
    0.46
     sensación
    0.45
     ያ
    0.44
     của
    0.44
    Act Density 0.188%

    No Known Activations