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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially periods

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

    package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.79
     iſt
    -0.69
    verwijspagina
    -0.68
     Anſ
    -0.67
     anſ
    -0.66
    ScopeManager
    -0.65
    TagHelper
    -0.64
     faſt
    -0.61
     juſ
    -0.61
     ſtand
    -0.60
    POSITIVE LOGITS
    .
    0.66
    ://
    0.46
    <h3>
    0.45
    <h1>
    0.45
     Human
    0.43
    ⓘ
    0.43
     Brun
    0.43
    ?
    0.43
    The
    0.42
     Dun
    0.42
    Act Density 0.008%

    No Known Activations