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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :text
    -0.08
    かい
    -0.06
     ballet
    -0.06
    ыш
    -0.06
    (xy
    -0.06
    (plot
    -0.06
     prostitu
    -0.06
    arta
    -0.06
    figure
    -0.06
     Assy
    -0.06
    POSITIVE LOGITS
     emerged
    0.08
     ArgumentException
    0.07
     VERBOSE
    0.06
    个
    0.06
     Modified
    0.06
    ervoir
    0.06
     متحده
    0.06
     LI
    0.06
     secure
    0.06
    ivation
    0.06
    Act Density 0.014%

    No Known Activations