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

    Neuronpedia

    INDEX
    Explanations

    Korean/Japanese characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flour
    -0.07
     кіль
    -0.06
    「……
    -0.06
    理解
    -0.06
     lick
    -0.06
     ingl
    -0.06
     Sh
    -0.06
     superiority
    -0.06
     Jasper
    -0.06
     الاخ
    -0.06
    POSITIVE LOGITS
    에
    0.08
     biblical
    0.07
    eným
    0.07
     onlara
    0.07
    _peak
    0.07
     enacted
    0.06
    ="./
    0.06
    시에
    0.06
    они
    0.06
     Patio
    0.06
    Act Density 0.010%

    No Known Activations