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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their context in the text

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

    Numbers with trailing digits

    np_acts-logits-general · gemini-2.0-flash

    numerical calculations quantity units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.54
     @"/
    -0.53
    AccessorTable
    -0.52
    RegressionTest
    -0.52
    .*")]
    -0.51
    CROSSTALK
    -0.50
    InputTagHelper
    -0.48
    лтамалар
    -0.48
    -0.47
    httphttps
    -0.47
    POSITIVE LOGITS
     Berechnung
    0.46
     calculated
    0.43
     calculations
    0.42
     arrep
    0.42
    zeera
    0.41
     termica
    0.40
     Calculation
    0.38
    listdir
    0.38
    odetic
    0.38
     calculation
    0.38
    Act Density 0.783%

    No Known Activations