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

    Neuronpedia

    INDEX
    Explanations

    references to reports or formal documents

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

    report, story, source, computational propaganda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.50
    KURZBESCHREIBUNG
    -0.47
    UseVisualStyle
    -0.44
    tvguidetime
    -0.43
     właśnie
    -0.42
    animaux
    -0.41
     amizade
    -0.40
     ambassade
    -0.40
     invitados
    -0.40
     graça
    -0.40
    POSITIVE LOGITS
    曖昧さ回避
    0.49
    <?
    0.45
    ⓧ
    0.43
    +#+#
    0.42
    もしろ
    0.42
     createSprite
    0.42
     Enlight
    0.39
    amoan
    0.39
     mdl
    0.39
    ImageContext
    0.38
    Act Density 0.000%

    No Known Activations