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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Modules
    -0.07
     cellar
    -0.07
    _reaction
    -0.06
     للح
    -0.06
     дерев
    -0.06
     GAS
    -0.06
     Terms
    -0.06
     Executors
    -0.06
    plugin
    -0.06
    basket
    -0.06
    POSITIVE LOGITS
    Guid
    0.08
     سال
    0.06
     숙
    0.06
     数
    0.06
    SSL
    0.06
    取
    0.06
     culturally
    0.06
     Guid
    0.06
    BMW
    0.06
    卷
    0.06
    Act Density 0.002%

    No Known Activations