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

    Neuronpedia

    INDEX
    Explanations

    surnames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NOWLED
    -0.06
    teří
    -0.06
    -width
    -0.06
     shifted
    -0.06
     каш
    -0.06
     pkg
    -0.06
     niż
    -0.06
     Right
    -0.06
    (block
    -0.06
     servants
    -0.06
    POSITIVE LOGITS
     [][]
    0.07
    theros
    0.06
     Percy
    0.06
    incy
    0.06
    xC
    0.06
    λης
    0.06
     BRAND
    0.06
     inconsistency
    0.06
     grades
    0.06
    ória
    0.06
    Act Density 0.083%

    No Known Activations