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

    Neuronpedia

    INDEX
    Explanations

    tooltip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Однак
    -0.07
     Lucy
    -0.07
    (shell
    -0.07
    Navigation
    -0.07
     cwd
    -0.07
     Marble
    -0.06
    	clock
    -0.06
     stack
    -0.06
     onPause
    -0.06
    uvre
    -0.06
    POSITIVE LOGITS
     tooltip
    0.12
    tooltip
    0.11
     Tooltip
    0.08
     tooltips
    0.07
    Tooltip
    0.07
     TI
    0.06
    ii
    0.06
    .EMAIL
    0.06
    -tooltip
    0.06
    蒂
    0.06
    Act Density 0.002%

    No Known Activations