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

    Neuronpedia

    INDEX
    Explanations

    negative and positive numerical values and indicators within a dataset

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

    Formatting from tables or data

    np_acts-logits-general · gemini-2.0-flash

    legal case contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    همچنین
    -0.56
    ttemberg
    -0.44
     Also
    -0.43
     ComVisible
    -0.43
    istisches
    -0.43
    <eos>
    -0.42
     heller
    -0.42
     /\.
    -0.41
    Also
    -0.41
     also
    -0.41
    POSITIVE LOGITS
     Савезне
    0.78
     tartalomajánló
    0.73
    ︎
    0.70
    VersionUID
    0.68
     okuyayım
    0.66
     للاسماء
    0.65
    Попис
    0.63
     beginnetje
    0.62
     createContext
    0.61
    pherals
    0.60
    Act Density 0.161%

    No Known Activations