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
    	args
    -0.07
     confess
    -0.07
     jedoch
    -0.07
    numbers
    -0.07
     trồng
    -0.07
    .gif
    -0.06
    /url
    -0.06
    _again
    -0.06
    .png
    -0.06
     maxHeight
    -0.06
    POSITIVE LOGITS
    출장안마
    0.06
     Uruguay
    0.06
    @login
    0.06
     �
    0.06
    668
    0.06
    (stage
    0.06
     Granite
    0.06
    .UltraWin
    0.06
    .InnerException
    0.06
    是一
    0.06
    Act Density 0.046%

    No Known Activations