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

    Neuronpedia

    INDEX
    Explanations

    nonlinear optical phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ристо
    0.56
     catalyzes
    0.51
    罗马
    0.50
    ья
    0.49
    н
    0.49
     comenzaron
    0.48
    هم
    0.48
    紗
    0.48
    来自于
    0.48
    ن
    0.47
    POSITIVE LOGITS
    f
    0.59
     guideline
    0.59
     Pandas
    0.59
     OTT
    0.57
    fords
    0.57
     firewall
    0.56
     racket
    0.56
     Daughter
    0.55
     generational
    0.55
     Bulldog
    0.55
    Act Density 0.001%

    No Known Activations