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

    Neuronpedia

    INDEX
    Explanations

    notification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	usage
    -0.08
     ais
    -0.08
    這一
    -0.07
     AI
    -0.07
    $path
    -0.07
     marché
    -0.07
    _activate
    -0.07
    uddle
    -0.07
    سه
    -0.07
    <pre
    -0.07
    POSITIVE LOGITS
     notification
    0.08
    ɦ
    0.07
    Notification
    0.07
    Debe
    0.07
    �
    0.07
    抗震
    0.07
     prohibits
    0.07
    (notification
    0.07
     Kon
    0.07
    Kon
    0.07
    Act Density 0.007%

    No Known Activations