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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Power
    -0.07
    surname
    -0.07
    Marvel
    -0.07
    一般
    -0.07
    Camb
    -0.07
    扆
    -0.06
    (serv
    -0.06
    mount
    -0.06
     syll
    -0.06
    力求
    -0.06
    POSITIVE LOGITS
     الأسبوع
    0.07
    fortawesome
    0.07
    이나
    0.07
     drains
    0.07
    ☨
    0.07
     ao
    0.06
    ﺥ
    0.06
     chặn
    0.06
    喟
    0.06
     FIFO
    0.06
    Act Density 0.020%

    No Known Activations