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

    Neuronpedia

    INDEX
    Explanations

    procurement or possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क
    2.40
     ordeal
    1.87
    ס
    1.71
    ingly
    1.69
    hug
    1.65
    tailed
    1.65
    TH
    1.60
    dang
    1.60
    ors
    1.56
    हिट
    1.53
    POSITIVE LOGITS
     thee
    2.26
     불구하고
    2.09
    imwrite
    2.01
    celikle
    1.99
    ﹋
    1.97
     luas
    1.94
     Ons
    1.88
     setIs
    1.88
    uzet
    1.87
     baryon
    1.86
    Act Density 0.000%

    No Known Activations