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

    Neuronpedia

    INDEX
    Explanations

    worse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YR
    -0.08
     حيث
    -0.07
    Á
    -0.07
    áns
    -0.07
     commun
    -0.07
     pron
    -0.07
    ুপ
    -0.07
     interp
    -0.07
    ાતા
    -0.07
     lexer
    -0.07
    POSITIVE LOGITS
     செயல
    0.08
     эта
    0.08
    rikstad
    0.07
     Isles
    0.07
    minimal
    0.07
     minimal
    0.07
    -masing
    0.07
     современные
    0.07
     சென்னை
    0.07
     Sena
    0.07
    Act Density 0.000%

    No Known Activations