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

    Neuronpedia

    INDEX
    Explanations

    numeric data or statistical values

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

    Numbers followed by periods

    np_acts-logits-general · gemini-2.0-flash

    doi links and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.71
    новништво
    -0.70
     fubject
    -0.70
    parsedMessage
    -0.69
     purpoſe
    -0.67
    ContentAlignment
    -0.66
     itſelf
    -0.64
    featureID
    -0.63
    :✨
    -0.61
    ModelForm
    -0.61
    POSITIVE LOGITS
    InstrumentedTest
    0.52
    Ehrungen
    0.48
    urio
    0.45
    )++;
    0.44
    ľov
    0.43
     lat
    0.42
    efty
    0.42
     verg
    0.42
    splan
    0.42
      (
    0.41
    Act Density 0.313%

    No Known Activations