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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eslint
    -0.07
    اساس
    -0.06
    Requires
    -0.06
     tails
    -0.06
    /project
    -0.06
    ridged
    -0.06
     تون
    -0.06
    “For
    -0.06
    _same
    -0.06
    单位
    -0.06
    POSITIVE LOGITS
    (plot
    0.06
     lingu
    0.06
    .Word
    0.06
    alesce
    0.06
    _MUTEX
    0.06
    	Object
    0.06
     XBOOLE
    0.06
    enden
    0.06
    ~↵
    0.06
     batch
    0.06
    Act Density 0.056%

    No Known Activations