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

    Neuronpedia

    INDEX
    Explanations

    Email addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ADHD
    -0.07
    胸口
    -0.07
    发电机
    -0.07
    선
    -0.06
     inviting
    -0.06
    Al
    -0.06
    wp
    -0.06
     precision
    -0.06
    udson
    -0.06
     const
    -0.06
    POSITIVE LOGITS
    +'\
    0.08
    roys
    0.07
     whites
    0.07
    .setMaximum
    0.07
    hare
    0.07
    ’m
    0.07
    _REFERER
    0.07
    _scr
    0.07
    .Middle
    0.07
    ROY
    0.07
    Act Density 0.004%

    No Known Activations