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

    Neuronpedia

    INDEX
    Explanations

    trigonometry formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decorators
    -0.08
    ాబు
    -0.08
     разобраться
    -0.08
    条例
    -0.08
     irritation
    -0.08
     irrit
    -0.08
     oh
    -0.07
    @n
    -0.07
     Jane
    -0.07
     χώ
    -0.07
    POSITIVE LOGITS
    -than
    0.09
    لل
    0.08
     často
    0.08
     häufig
    0.08
     ofta
    0.08
    -positive
    0.08
    fold
    0.08
     souvent
    0.07
    သော
    0.07
     olum
    0.07
    Act Density 0.008%

    No Known Activations