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

    Neuronpedia

    INDEX
    Explanations

    identifiers and URLs in the text

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

    URLs and IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.87
     المعيارى
    -0.75
    chieht
    -0.73
     desmotivaciones
    -0.69
    BagConstraints
    -0.68
     finanzas
    -0.65
     sugerencias
    -0.65
     çat
    -0.65
     klant
    -0.64
     verdades
    -0.64
    POSITIVE LOGITS
    TypeID
    0.71
     getID
    0.68
     gonzález
    0.64
    ID
    0.63
    URL
    0.62
    xFFFFFFFF
    0.61
    HTTPClient
    0.59
    IDs
    0.59
    UserID
    0.59
    API
    0.56
    Act Density 0.039%

    No Known Activations