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

    Neuronpedia

    INDEX
    Explanations

    SQL commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    接管
    -0.08
    (simp
    -0.07
    ank
    -0.07
    ief
    -0.07
    廟
    -0.07
    劂
    -0.07
    دافع
    -0.07
     fearless
    -0.06
    arı
    -0.06
     Sanity
    -0.06
    POSITIVE LOGITS
    -oriented
    0.07
    ჩ
    0.07
    -enabled
    0.07
     ($.
    0.07
    プロジェ
    0.06
    /se
    0.06
    Compile
    0.06
     Decomp
    0.06
     />\
    0.06
    OrElse
    0.06
    Act Density 0.006%

    No Known Activations