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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bist
    -0.09
    Wer
    -0.08
     intemp
    -0.08
    Better
    -0.07
     HAN
    -0.07
    tk
    -0.07
    Provides
    -0.07
    Hans
    -0.07
     glycol
    -0.07
    Network
    -0.07
    POSITIVE LOGITS
     знак
    0.08
     Wolfe
    0.08
     Nas
    0.08
     anus
    0.07
    	unset
    0.07
     Stool
    0.07
     пользователь
    0.07
    雄
    0.07
     trat
    0.07
    身体
    0.07
    Act Density 0.001%

    No Known Activations