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

    Neuronpedia

    INDEX
    Explanations

    code blocks and code-related terms in the document.

    oai_token-act-pair · gemini-2.0-flash

    words with specific suffix patterns

    np_token-act-pair-logits · gpt-4o-mini

    Non-English fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SuppressMessage
    -0.69
    featureID
    -0.62
    onViewCreated
    -0.59
    ScopeManager
    -0.58
    UnusedPrivate
    -0.58
     kaynağından
    -0.57
    ModelSerializer
    -0.57
    [++
    -0.57
    ')";
    -0.56
     wikipagina
    -0.55
    POSITIVE LOGITS
    thra
    0.53
    voy
    0.49
    μών
    0.49
    omini
    0.47
    ře
    0.47
     moulin
    0.47
    afat
    0.47
     نف
    0.47
    korb
    0.46
    escu
    0.45
    Act Density 0.851%

    No Known Activations