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

    Neuronpedia

    INDEX
    Explanations

    instructions and parameters related to rounding numerical values

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

    Rounding a number to specified decimal places

    np_acts-logits-general · gemini-2.0-flash

    rounding to decimal places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LineColor
    -0.46
     defaultstate
    -0.45
     مبار
    -0.43
     stoff
    -0.43
     Kante
    -0.42
    content
    -0.41
     Eng
    -0.41
    Favor
    -0.41
    tides
    -0.40
     Contenido
    -0.39
    POSITIVE LOGITS
     accuracy
    1.93
     precision
    1.68
     Accuracy
    1.63
    accuracy
    1.55
     accurate
    1.52
    Accuracy
    1.51
    precision
    1.42
     ACCUR
    1.38
    accurate
    1.38
     Precision
    1.34
    Act Density 0.659%

    No Known Activations