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

    Neuronpedia

    INDEX
    Explanations

    obtaining approval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traps
    -0.07
    .constraint
    -0.06
    "But
    -0.06
    [random
    -0.06
    timeout
    -0.06
     crawl
    -0.06
    _Con
    -0.06
    _uuid
    -0.06
    .non
    -0.06
    оне
    -0.06
    POSITIVE LOGITS
    elopment
    0.06
    eltas
    0.06
    บบ
    0.06
     Foam
    0.06
    -defined
    0.06
    comparison
    0.06
     dimin
    0.06
    ismatch
    0.06
     рекомендуется
    0.06
    FILENAME
    0.06
    Act Density 0.003%

    No Known Activations