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

    Neuronpedia

    INDEX
    Explanations

    numerical ratios and their representations in various formats

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

    ratios and proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.71
    featureID
    -0.65
    bootstrapcdn
    -0.63
    iſen
    -0.63
    rbrakk
    -0.63
    anthene
    -0.63
    /**
    -0.63
    ſchaft
    -0.62
    UnitTesting
    -0.62
     queſta
    -0.61
    POSITIVE LOGITS
     ratio
    0.91
     ratios
    0.74
    ratio
    0.71
     Ratio
    0.68
     RATIO
    0.63
    Ratio
    0.62
     Ratios
    0.57
    ratios
    0.55
    RATIO
    0.54
     proportion
    0.35
    Act Density 0.215%

    No Known Activations