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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    芍
    -0.08
     SAM
    -0.07
    Nam
    -0.07
     spar
    -0.07
    Qu
    -0.07
    봄
    -0.07
    就可以了
    -0.07
     shoulder
    -0.07
     SP
    -0.07
     WON
    -0.07
    POSITIVE LOGITS
     자체
    0.08
    .fail
    0.07
    Tester
    0.07
    kelig
    0.07
    xCC
    0.07
     mechanically
    0.07
     Kirk
    0.07
    区域
    0.07
     Jahre
    0.06
    ulk
    0.06
    Act Density 0.002%

    No Known Activations