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

    Neuronpedia

    INDEX
    Explanations

    programming generics/parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mixes
    -0.07
    �
    -0.07
     Coleman
    -0.07
    大幅提升
    -0.06
     lu
    -0.06
    暾
    -0.06
    獬
    -0.06
    ಯ
    -0.06
    囵
    -0.06
     lap
    -0.06
    POSITIVE LOGITS
    拆迁
    0.07
    _zones
    0.07
     empire
    0.07
    _slots
    0.07
    _filepath
    0.06
    SetActive
    0.06
    مري
    0.06
    網站
    0.06
    .startsWith
    0.06
    �
    0.06
    Act Density 0.025%

    No Known Activations