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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate estimations or projections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Estimates with numbers or percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     particulière
    -0.46
     específicamente
    -0.46
     necesariamente
    -0.46
    verifyException
    -0.45
     Relaciones
    -0.44
     questão
    -0.44
     nemlig
    -0.43
     Soporte
    -0.42
     particulières
    -0.42
     fundamentales
    -0.42
    POSITIVE LOGITS
     estimate
    0.84
     estimated
    0.84
     Estimated
    0.75
     estimés
    0.75
    Estimated
    0.75
     Estimate
    0.75
     estimates
    0.74
    estimated
    0.71
     Estimates
    0.69
     estimating
    0.67
    Act Density 0.019%

    No Known Activations