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

    Neuronpedia

    INDEX
    Explanations

    keywords related to formal communication or documentation

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

    followed by quotations or citations

    np_acts-logits-general · gemini-2.0-flash

    making statements or confessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viited
    -0.46
     aerobic
    -0.42
    siempre
    -0.40
     ModelExpression
    -0.40
     kasarigan
    -0.39
     سكانية
    -0.39
     always
    -0.39
     vast
    -0.38
     human
    -0.38
     coherent
    -0.37
    POSITIVE LOGITS
    0.56
    évaluateur
    0.56
     ligiloj
    0.53
    verwijspagina
    0.51
    centralwidget
    0.50
    devamını
    0.49
    <?
    0.47
     виправивши
    0.47
    ollectionView
    0.45
    ]";
    0.45
    Act Density 0.702%

    No Known Activations