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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stackpath
    -0.06
    ська
    -0.06
     Stir
    -0.06
    	dt
    -0.06
    ifix
    -0.06
    hir
    -0.06
     Roe
    -0.06
     pid
    -0.06
    .startTime
    -0.05
    .db
    -0.05
    POSITIVE LOGITS
     procedure
    0.08
    (editor
    0.07
    -policy
    0.07
     collects
    0.07
     Procedure
    0.07
     offer
    0.07
    .abort
    0.06
     Efficiency
    0.06
     Illegal
    0.06
    .Process
    0.06
    Act Density 0.000%

    No Known Activations