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

    Neuronpedia

    INDEX
    Explanations

    superpowers descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Куб
    -0.07
    "]->
    -0.07
     Opening
    -0.06
    建設
    -0.06
    ствие
    -0.06
    	RTLI
    -0.06
    험
    -0.06
     рецепт
    -0.06
    Star
    -0.06
     رف
    -0.06
    POSITIVE LOGITS
    bler
    0.08
    ana
    0.07
    onia
    0.07
    osoph
    0.06
     Insights
    0.06
     않은
    0.06
    né
    0.06
    líč
    0.06
    353
    0.06
    ög
    0.06
    Act Density 0.067%

    No Known Activations