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

    Neuronpedia

    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    次数
    -0.07
     Wednesday
    -0.06
     captcha
    -0.06
     соци
    -0.06
     payments
    -0.06
     Thursday
    -0.06
     bych
    -0.06
     Stap
    -0.06
     getch
    -0.05
    	mouse
    -0.05
    POSITIVE LOGITS
     watershed
    0.07
    $$$$
    0.06
    명을
    0.06
     illuminated
    0.06
     주문
    0.06
    probably
    0.06
     PAT
    0.06
     *)↵
    0.06
    /Private
    0.06
    setImage
    0.06
    Act Density 0.027%

    No Known Activations