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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的大
    -0.07
     خودش
    -0.07
     kendisini
    -0.06
    işti
    -0.06
    ौज
    -0.06
    .MapFrom
    -0.06
     يح
    -0.06
    (pub
    -0.06
    ,↵↵↵
    -0.06
    etween
    -0.06
    POSITIVE LOGITS
     particip
    0.07
     ελλην
    0.07
    _CLASS
    0.07
    acic
    0.06
    Thousands
    0.06
     GG
    0.06
    eger
    0.06
     Alg
    0.06
    بل
    0.06
     SENSOR
    0.06
    Act Density 0.000%

    No Known Activations