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

    Neuronpedia

    INDEX
    Explanations

    manage, KPI, potential, delays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buch
    0.48
     negativ
    0.46
     Gonz
    0.44
     GLS
    0.44
     gör
    0.44
     Pauline
    0.44
    ABLISHED
    0.43
     Schell
    0.43
    साठी
    0.42
    IRT
    0.42
    POSITIVE LOGITS
    我会
    0.43
    реги
    0.41
    વતી
    0.40
    ጬ
    0.40
     অচ
    0.38
     osztály
    0.38
    n
    0.38
    fontWeight
    0.38
    名を
    0.38
    ንዳንድ
    0.37
    Act Density 0.001%

    No Known Activations