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

    Neuronpedia

    INDEX
    Explanations

    memories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     angles
    -0.06
     меди
    -0.06
     iyi
    -0.06
    _binding
    -0.06
     rape
    -0.06
    akistan
    -0.06
    imizi
    -0.06
     offsetof
    -0.06
     cuando
    -0.06
     ileri
    -0.06
    POSITIVE LOGITS
     GH
    0.07
    -none
    0.07
    яг
    0.07
     Blanch
    0.07
    ffffff
    0.06
    .gb
    0.06
     مس
    0.06
     lạ
    0.06
    .Generic
    0.06
     зам
    0.06
    Act Density 0.027%

    No Known Activations