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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edmund
    -0.08
    Invalid
    -0.07
    深入人心
    -0.07
     открыт
    -0.07
    cliffe
    -0.07
     perpetual
    -0.07
     pdf
    -0.07
    ilk
    -0.07
    ึก
    -0.07
    illard
    -0.06
    POSITIVE LOGITS
    Sizer
    0.07
     fault
    0.07
    ጨ
    0.07
    座
    0.07
    缠
    0.07
    сор
    0.06
    蜀
    0.06
    ILING
    0.06
    一圈
    0.06
    .Design
    0.06
    Act Density 0.002%

    No Known Activations