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

    Neuronpedia

    INDEX
    Explanations

    terms associated with qualifications and expertise

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

    most superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.62
    CloseOperation
    -0.61
    MLLoader
    -0.60
    parsedMessage
    -0.60
     الرياضيه
    -0.58
    tagHelperRunner
    -0.58
    DoubleQuotes
    -0.56
    Personendaten
    -0.56
    tonode
    -0.54
    featureID
    -0.53
    POSITIVE LOGITS
     strongest
    0.94
     most
    0.92
     가장
    0.89
     heaviest
    0.88
    最も
    0.88
     greatest
    0.87
     hardest
    0.85
     clearest
    0.85
     widest
    0.84
    ziest
    0.84
    Act Density 0.400%

    No Known Activations