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

    Neuronpedia

    INDEX
    Explanations

    sections of text with no significant content or activations

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

    Appears before places or names

    np_acts-logits-general · gemini-2.0-flash

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.70
    ########.
    -0.67
    AndEndTag
    -0.65
    :+:
    -0.61
    tagena
    -0.54
    WEBPACK
    -0.54
    pdev
    -0.54
     suppose
    -0.54
    "]();
    -0.53
    trä
    -0.53
    POSITIVE LOGITS
     undersigned
    0.72
     alfo
    0.62
     GUARANTE
    0.60
     specialties
    0.59
     Chrift
    0.58
     neceff
    0.58
     unsurpassed
    0.57
    nocześnie
    0.56
     fuper
    0.56
     reafon
    0.56
    Act Density 0.030%

    No Known Activations