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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _loading
    -0.07
    fk
    -0.07
    mek
    -0.07
    يران
    -0.07
    zan
    -0.07
    обще
    -0.07
     handle
    -0.06
    不知不觉
    -0.06
     pes
    -0.06
     mile
    -0.06
    POSITIVE LOGITS
     ----------↵
    0.08
    Subject
    0.07
     Representative
    0.07
     Programme
    0.07
    ecture
    0.07
     Oilers
    0.07
     Perth
    0.06
    ︺
    0.06
     Artist
    0.06
    おすすめ
    0.06
    Act Density 0.087%

    No Known Activations