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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Karlov
    -0.08
     CAMERA
    -0.07
     MISS
    -0.07
    [p
    -0.06
     rẻ
    -0.06
     เป
    -0.06
    	s
    -0.06
    ('.
    -0.06
     XR
    -0.06
    PN
    -0.06
    POSITIVE LOGITS
    Ấ
    0.07
    sah
    0.07
    Emer
    0.06
    175
    0.06
     musique
    0.06
     araya
    0.06
    	select
    0.06
     sayesinde
    0.06
    ialis
    0.06
    оци
    0.06
    Act Density 0.003%

    No Known Activations