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

    Neuronpedia

    INDEX
    Explanations

    universe beyond organization needs and impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脖
    0.51
    事的
    0.50
    ofType
    0.49
     மு
    0.49
    梦
    0.48
     McGuire
    0.47
    աց
    0.47
    aksikan
    0.46
    тено
    0.46
    iveau
    0.46
    POSITIVE LOGITS
     elasticity
    0.53
     defects
    0.50
     fama
    0.48
     grat
    0.47
     curve
    0.46
     courbe
    0.46
     operand
    0.45
     corsa
    0.45
     azimuth
    0.45
     elastic
    0.44
    Act Density 0.000%

    No Known Activations