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

    Neuronpedia

    INDEX
    Explanations

    brightly lit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وف
    0.56
    事先
    0.55
    皮革
    0.54
    馬
    0.51
    白
    0.50
     رياضيات
    0.49
    存
    0.48
    餒
    0.48
     semblance
    0.48
    杯
    0.48
    POSITIVE LOGITS
    ,
    0.51
    ão
    0.50
    n
    0.49
    im
    0.46
    ubar
    0.46
    isy
    0.45
    Gen
    0.45
    rot
    0.44
     unapolog
    0.44
    genos
    0.44
    Act Density 0.000%

    No Known Activations