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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (len
    -0.07
    .Empty
    -0.07
    lesh
    -0.06
     discussed
    -0.06
    	open
    -0.06
    🕒
    -0.06
    �
    -0.06
    חוץ
    -0.06
     DEST
    -0.06
    ever
    -0.06
    POSITIVE LOGITS
     Kay
    0.07
    (ticket
    0.07
    >({↵
    0.07
    $config
    0.07
    _minimum
    0.07
     Moderator
    0.07
    \Container
    0.07
    _winner
    0.07
     investigator
    0.07
     scriptures
    0.07
    Act Density 0.016%

    No Known Activations