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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    강
    -0.07
    ्व
    -0.07
    하여
    -0.07
    ूद
    -0.07
     foremost
    -0.07
    ascending
    -0.07
     kr
    -0.06
    زب
    -0.06
    null
    -0.06
     versch
    -0.06
    POSITIVE LOGITS
     Vide
    0.07
    _cache
    0.06
    ائي
    0.06
     subscribe
    0.06
    Delayed
    0.06
     Shop
    0.06
     Dysfunction
    0.06
    _pic
    0.06
    (Roles
    0.06
    _Instance
    0.06
    Act Density 0.001%

    No Known Activations