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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     찬
    -0.06
     XF
    -0.06
    essen
    -0.06
    انس
    -0.06
     Scrap
    -0.06
    _called
    -0.06
    (crate
    -0.06
    وره
    -0.06
    Disk
    -0.06
     Chess
    -0.06
    POSITIVE LOGITS
    	player
    0.07
    pressions
    0.07
    arer
    0.07
     oy
    0.07
     ██
    0.06
    <ul
    0.06
     notifying
    0.06
    	tag
    0.06
     servings
    0.06
     commander
    0.06
    Act Density 0.000%

    No Known Activations