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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers indicating ranking or order

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

    ordinal followed by size/ranking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     väl
    -0.30
    unjukan
    -0.27
     Vorlage
    -0.25
     feux
    -0.24
     Montevideo
    -0.24
    ต
    -0.24
     baños
    -0.23
     Strecken
    -0.23
     consiglio
    -0.23
     Gestaltung
    -0.23
    POSITIVE LOGITS
    rungsseite
    0.93
     betweenstory
    0.84
    transQ
    0.75
    featureID
    0.74
    NameInMap
    0.72
     Савезне
    0.69
    windowFixed
    0.68
    +:+
    0.68
    ThroughAttribute
    0.66
     Réponses
    0.65
    Act Density 0.023%

    No Known Activations