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

    Neuronpedia

    INDEX
    Explanations

    definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	offset
    -0.07
    三
    -0.07
     tension
    -0.06
     GAME
    -0.06
    explicit
    -0.06
    /loader
    -0.06
    .circular
    -0.06
     ztr
    -0.06
    -property
    -0.06
    cour
    -0.06
    POSITIVE LOGITS
    (Label
    0.07
    .extent
    0.06
     succes
    0.06
    _es
    0.06
    lbs
    0.06
    datepicker
    0.06
    Ln
    0.06
    در
    0.06
     المن
    0.06
    _pickle
    0.06
    Act Density 0.195%

    No Known Activations