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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that indicate approximations or estimates of measurements

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

    approximation or estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vegetación
    -0.34
    paravant
    -0.33
    queles
    -0.32
     bricolaje
    -0.32
     jednocześnie
    -0.32
     getUserId
    -0.31
     getRule
    -0.31
     fundamentos
    -0.30
     calentamiento
    -0.30
     nueces
    -0.30
    POSITIVE LOGITS
    awtextra
    0.94
    Approx
    0.85
     Approx
    0.85
     approx
    0.83
    approx
    0.79
     Wicidata
    0.73
    InjectAttribute
    0.71
    ConstraintMaker
    0.69
    makeConstraints
    0.69
     disambiguazione
    0.69
    Act Density 0.013%

    No Known Activations