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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نیز
    -0.07
     MILL
    -0.07
    ньому
    -0.07
    啪
    -0.06
     drum
    -0.06
     Randall
    -0.06
     Medicine
    -0.06
    ังจาก
    -0.06
     similarities
    -0.06
     RETURN
    -0.06
    POSITIVE LOGITS
    .Standard
    0.07
    (optarg
    0.07
    	bg
    0.07
     disqualified
    0.06
    .forEach
    0.06
    /octet
    0.06
     겨
    0.06
    stdarg
    0.06
    csrf
    0.06
    []>↵
    0.06
    Act Density 0.000%

    No Known Activations