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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     своей
    -0.07
    udit
    -0.06
     řid
    -0.06
    Hunter
    -0.06
     Nüfus
    -0.06
    064
    -0.06
    bero
    -0.06
    เอก
    -0.06
    лагод
    -0.06
     cruc
    -0.06
    POSITIVE LOGITS
    ↵            ↵
    0.06
    Circular
    0.06
    ":{"
    0.06
    "){
↵
    0.06
     Des
    0.06
    fuscated
    0.06
    coder
    0.06
    keleton
    0.06
    abox
    0.06
    (button
    0.06
    Act Density 0.013%

    No Known Activations