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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    年
    -0.08
     yours
    -0.07
     Moore
    -0.07
     امور
    -0.07
     lãi
    -0.06
    FLASH
    -0.06
    ?-
    -0.06
    ặp
    -0.06
    Single
    -0.06
    CHECK
    -0.06
    POSITIVE LOGITS
     अक
    0.06
     Edu
    0.06
    _tF
    0.06
    ug
    0.06
     düşünc
    0.06
    relevant
    0.06
    fonts
    0.06
    _CUDA
    0.06
    ФЛ
    0.06
     disrespectful
    0.06
    Act Density 0.106%

    No Known Activations