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

    Neuronpedia

    INDEX
    Explanations

    levels or degrees

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зан
    0.58
    蛩
    0.56
    xD
    0.55
    用
    0.55
     används
    0.54
    USING
    0.53
    spine
    0.53
    X
    0.52
    ستخدم
    0.52
     muertos
    0.51
    POSITIVE LOGITS
     Hd
    0.64
     HD
    0.61
     Went
    0.61
     Constit
    0.57
    कल्
    0.57
     Ан
    0.56
     Ollie
    0.56
     ৩৮
    0.56
     Ola
    0.55
     कल्
    0.55
    Act Density 0.000%

    No Known Activations