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

    Neuronpedia

    INDEX
    Explanations

    Short prefixes/fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.75
    WriteBarrier
    -0.69
     насељу
    -0.67
    ⓧ
    -0.64
    Hentet
    -0.57
    فحة
    -0.55
    RectangleBorder
    -0.53
     eventdata
    -0.52
    ிகள்
    -0.52
     Paglinawan
    -0.51
    POSITIVE LOGITS
     pre
    0.86
     hit
    0.68
    pre
    0.65
     bur
    0.63
    Pre
    0.61
     Pre
    0.60
     pré
    0.59
     per
    0.59
    hit
    0.56
    Hit
    0.56
    Act Density 0.002%

    No Known Activations