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

    Neuronpedia

    INDEX
    Explanations

    code/string manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realizar
    -0.07
    ogle
    -0.07
     makes
    -0.07
     brunch
    -0.06
     superstar
    -0.06
    _country
    -0.06
     meteor
    -0.06
     climbs
    -0.06
     charity
    -0.06
     imz
    -0.06
    POSITIVE LOGITS
    Formula
    0.07
    >t
    0.07
    [],↵
    0.07
     ld
    0.06
    	bs
    0.06
     polov
    0.06
    ,\↵
    0.06
    thinking
    0.06
    олод
    0.06
     davidjl
    0.06
    Act Density 0.056%

    No Known Activations