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

    Neuronpedia

    INDEX
    Explanations

    biological classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     P
    0.44
     B
    0.43
     ochr
    0.42
     Lest
    0.42
     zašt
    0.40
    )^
    0.40
     nez
    0.39
     الب
    0.39
    SSL
    0.38
     Méd
    0.38
    POSITIVE LOGITS
    VICIO
    0.43
     схе
    0.42
    闿
    0.41
     නිර්
    0.39
     suggestions
    0.39
    姮
    0.39
    OfString
    0.38
    anyak
    0.38
     profiled
    0.38
     effekt
    0.38
    Act Density 0.000%

    No Known Activations