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

    Neuronpedia

    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leider
    -0.07
     الض
    -0.07
    538
    -0.06
     жал
    -0.06
     есте
    -0.06
    _STENCIL
    -0.06
    票
    -0.06
    fila
    -0.06
     frosting
    -0.06
    ABCDE
    -0.06
    POSITIVE LOGITS
     Potter
    0.09
     потом
    0.08
     pottery
    0.08
     Democrats
    0.07
    esti
    0.07
    ware
    0.07
     potom
    0.07
    _Account
    0.07
    arcer
    0.07
    νά
    0.07
    Act Density 0.011%

    No Known Activations