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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scared
    -0.08
    .where
    -0.08
     paired
    -0.07
     SQL
    -0.07
     Ancient
    -0.07
     sudden
    -0.07
     Dx
    -0.07
    很容易
    -0.07
     ROUND
    -0.07
    AsString
    -0.07
    POSITIVE LOGITS
    arnation
    0.07
     işletme
    0.07
    ']):↵
    0.06
     деят
    0.06
    lane
    0.06
    severity
    0.06
     reform
    0.06
    pieczeńst
    0.06
     conservatives
    0.06
    关停
    0.06
    Act Density 0.000%

    No Known Activations