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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    婠
    -0.07
    톈
    -0.07
    ﰿ
    -0.06
    叚
    -0.06
     Movement
    -0.06
    ₵
    -0.06
    רוט
    -0.06
    同类
    -0.06
    잏
    -0.06
     פו
    -0.06
    POSITIVE LOGITS
     .
↵
    0.09
    鲈
    0.08
    -loving
    0.07
    iter
    0.07
     psychiatrist
    0.07
    __(↵
    0.07
    .Rectangle
    0.07
    .parseFloat
    0.06
     Physiology
    0.06
    uil
    0.06
    Act Density 0.002%

    No Known Activations