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

    Neuronpedia

    INDEX
    Explanations

    Clarifications and definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Camera
    -0.07
     penny
    -0.07
    ounce
    -0.06
     ре
    -0.06
     hearings
    -0.06
    algo
    -0.06
    网站
    -0.06
    '.↵
    -0.06
    рг
    -0.06
     м
    -0.06
    POSITIVE LOGITS
     домаш
    0.07
     �
    0.06
    ้ต
    0.06
    �
    0.06
    .setPrototypeOf
    0.06
    .'</
    0.06
    .up
    0.06
    .AutoSizeMode
    0.06
    ●●●●●●●●
    0.06
     gifs
    0.06
    Act Density 0.086%

    No Known Activations