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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mma
    -0.07
    etermination
    -0.07
    ул
    -0.07
     Nd
    -0.07
     Lion
    -0.07
     الخيار
    -0.07
    uro
    -0.07
    _variant
    -0.06
    .community
    -0.06
    ᴴ
    -0.06
    POSITIVE LOGITS
    产学研
    0.07
    新陈
    0.07
    빵
    0.06
    מפורט
    0.06
    덤
    0.06
    Ὕ
    0.06
    اقتص
    0.06
     Than
    0.06
     than
    0.06
     sodom
    0.06
    Act Density 0.022%

    No Known Activations