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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and functions in code snippets

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

    Appears before a single-letter token

    np_acts-logits-general · gemini-2.0-flash

    file command codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    -0.61
    a
    -0.60
    i
    -0.60
    e
    -0.59
    <strong>
    -0.58
    <b>
    -0.56
    <em>
    -0.55
    ة
    -0.54
    y
    -0.54
    oid
    -0.54
    POSITIVE LOGITS
     beginnetje
    0.98
    AddTagHelper
    0.89
    DockStyle
    0.88
     sherds
    0.84
    0.81
     ISNI
    0.80
     betweenstory
    0.79
     Abp
    0.78
     privatisation
    0.76
     виправивши
    0.76
    Act Density 1.074%

    No Known Activations