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

    Neuronpedia

    INDEX
    Explanations

    structured data attributes related to items and records

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

    Immediately follows punctuation or brackets

    np_acts-logits-general · gemini-2.0-flash

    key-value pairs in structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     named
    -0.94
     Named
    -0.82
     name
    -0.81
    Named
    -0.80
    Name
    -0.77
     Name
    -0.77
     naming
    -0.75
    named
    -0.74
     nommé
    -0.73
    名为
    -0.70
    POSITIVE LOGITS
     المعيارى
    0.80
    WriteAttribute
    0.66
    Portail
    0.57
    IVersion
    0.56
     referenties
    0.56
     description
    0.56
    hamshire
    0.54
     SUDOC
    0.54
     оригіналу
    0.54
     descrit
    0.53
    Act Density 0.398%

    No Known Activations