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

    Neuronpedia

    INDEX
    Explanations

    USD, BSD, aird, RD, aead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zyć
    0.54
    ುವುದಿಲ್ಲ
    0.52
    urde
    0.47
    imble
    0.46
    აც
    0.45
    ogonal
    0.45
    ುವುದು
    0.45
    담당
    0.45
    adai
    0.45
    ábor
    0.44
    POSITIVE LOGITS
    ଼
    0.83
    elivery
    0.73
    ynamic
    0.67
    ynamics
    0.63
    irect
    0.59
    imensional
    0.57
    ependence
    0.56
    ependent
    0.55
    iamond
    0.55
    ienst
    0.55
    Act Density 0.073%

    No Known Activations