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

    Neuronpedia

    INDEX
    Explanations

    Legal rulings/court orders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     внешне
    -0.08
     seized
    -0.07
     originating
    -0.07
     imagined
    -0.07
     restriction
    -0.07
    .mkdir
    -0.07
    极大的
    -0.07
    氨
    -0.07
     created
    -0.07
    +[
    -0.07
    POSITIVE LOGITS
     SHOULD
    0.07
    姿势
    0.07
     Gentle
    0.07
    ÖZ
    0.06
     CORPOR
    0.06
    ㅣ
    0.06
    #w
    0.06
    ㅑ
    0.06
    Ir
    0.06
    Պ
    0.06
    Act Density 0.040%

    No Known Activations