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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Snap
    -0.07
    -*
    -0.07
     FBI
    -0.07
    ako
    -0.07
    ptom
    -0.07
     manipulated
    -0.06
     PAD
    -0.06
    "))
    -0.06
    -height
    -0.06
    Esc
    -0.06
    POSITIVE LOGITS
     slogans
    0.08
    conscious
    0.06
    .WriteString
    0.06
    alking
    0.06
     Busty
    0.06
    interrupt
    0.06
     ${(
    0.06
    racak
    0.06
    aversable
    0.06
    	sd
    0.06
    Act Density 0.002%

    No Known Activations