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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wik
    -0.07
     مليون
    -0.07
     العلم
    -0.07
    Pick
    -0.07
     gastro
    -0.07
    为中心
    -0.07
     nut
    -0.07
     sik
    -0.07
    }%
    -0.07
     Liber
    -0.06
    POSITIVE LOGITS
     overwritten
    0.08
    ısı
    0.07
     oraz
    0.07
    قارب
    0.07
    重中之
    0.07
    额度
    0.07
    wu
    0.07
    _THAN
    0.06
    ":"","
    0.06
     ajout
    0.06
    Act Density 0.001%

    No Known Activations