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

    Neuronpedia

    INDEX
    Explanations

    code/system output

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Entities
    -0.07
    埫
    -0.07
    lear
    -0.07
    .UTC
    -0.07
    ительно
    -0.07
    �
    -0.07
    texts
    -0.07
    笫
    -0.06
    ها
    -0.06
    ℠
    -0.06
    POSITIVE LOGITS
    素晴らしい
    0.07
     Gordon
    0.07
     Eclipse
    0.07
    eldorf
    0.07
    根源
    0.07
    你要
    0.07
    _FIXED
    0.06
    .handler
    0.06
     Porto
    0.06
    Take
    0.06
    Act Density 0.006%

    No Known Activations