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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tek
    -0.08
    rve
    -0.06
     collage
    -0.06
     сф
    -0.06
     DOS
    -0.06
    pluck
    -0.06
    tests
    -0.06
     رئيس
    -0.06
     Fashion
    -0.06
     pigs
    -0.06
    POSITIVE LOGITS
     그는
    0.07
     (--
    0.07
     zelf
    0.07
    …"↵↵
    0.06
     Gemini
    0.06
    Leo
    0.06
    ическим
    0.06
    .Utc
    0.06
    QUIRES
    0.06
     TestData
    0.06
    Act Density 0.042%

    No Known Activations