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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and requests for rounding numbers

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

    rounding numbers to precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.64
    évaluateur
    -0.63
     otomatig
    -0.61
     Taktlose
    -0.57
    parsedMessage
    -0.55
    (!__
    -0.52
    findpost
    -0.50
    IntoConstraints
    -0.49
    IVEREF
    -0.49
     "));
    -0.49
    POSITIVE LOGITS
     rounding
    0.94
    Rounding
    0.82
     rounded
    0.63
     redonde
    0.61
    rounding
    0.60
    Round
    0.58
     Round
    0.51
    Rounded
    0.48
     Rounded
    0.47
     round
    0.47
    Act Density 0.036%

    No Known Activations