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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kapı
    -0.08
    抽取
    -0.07
     ambigu
    -0.07
     europé
    -0.07
     portray
    -0.07
    (I
    -0.07
     tamp
    -0.06
     cerco
    -0.06
    经贸
    -0.06
     cryptography
    -0.06
    POSITIVE LOGITS
    Ⱑ
    0.07
     נה
    0.07
    썜
    0.06
    ㈹
    0.06
     stainless
    0.06
     fold
    0.06
     Valid
    0.06
    똔
    0.06
     initializer
    0.06
    .LayoutControlItem
    0.06
    Act Density 0.002%

    No Known Activations