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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的空间
    -0.08
     Landscape
    -0.07
    nten
    -0.07
    .epoch
    -0.07
     ../../
    -0.07
    lene
    -0.07
    AnimationsModule
    -0.07
    ductory
    -0.07
     Parameter
    -0.07
     neural
    -0.07
    POSITIVE LOGITS
    talk
    0.07
    .biz
    0.07
    fra
    0.07
    izo
    0.07
    츄
    0.06
    ww
    0.06
     bal
    0.06
     BALL
    0.06
    ivery
    0.06
     flurry
    0.06
    Act Density 0.118%

    No Known Activations