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

    Neuronpedia

    INDEX
    Explanations

    broad

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ty
    0.70
    jom
    0.65
    ცი
    0.63
    żyt
    0.63
    zell
    0.62
    ्त
    0.58
    ాలే
    0.58
     کردہ
    0.57
     Cal
    0.57
    ствен
    0.57
    POSITIVE LOGITS
     ша
    0.75
     অবিশ্বাস্য
    0.69
    Higher
    0.69
    ename
    0.67
     टोटल
    0.67
    Tact
    0.66
    atiquement
    0.66
    ഷേ
    0.65
     implicated
    0.65
     психи
    0.64
    Act Density 0.020%

    No Known Activations