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

    Neuronpedia

    INDEX
    Explanations

    Date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нор
    -0.08
     fich
    -0.07
     col
    -0.07
    مل
    -0.07
    stands
    -0.06
    탄
    -0.06
    ewidth
    -0.06
     necesita
    -0.06
    @$
    -0.06
     части
    -0.06
    POSITIVE LOGITS
    _REFERENCE
    0.07
    遇
    0.06
    ,index
    0.06
    .success
    0.06
    Архівовано
    0.06
    Initializer
    0.06
     reflecting
    0.06
    (kv
    0.06
     jist
    0.06
    OPSIS
    0.06
    Act Density 0.002%

    No Known Activations