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

    Neuronpedia

    INDEX
    Explanations

    punctuation and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?f
    -0.07
     temporary
    -0.07
    汗
    -0.06
    -independent
    -0.06
     ammunition
    -0.06
    _bold
    -0.06
    unning
    -0.06
    mam
    -0.06
     clothes
    -0.06
     misplaced
    -0.06
    POSITIVE LOGITS
    医院
    0.06
     česk
    0.06
    	DECLARE
    0.06
    RED
    0.06
     поль
    0.06
     용
    0.06
     新
    0.06
     обязательно
    0.06
     связи
    0.06
    。而
    0.06
    Act Density 0.187%

    No Known Activations