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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inquiry or investigation into scientific concepts and relationships

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

    explaining or investigating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.75
     MainAxisSize
    -0.66
    UrlResolution
    -0.61
    istoitu
    -0.58
    parsedMessage
    -0.54
     propOrder
    -0.53
    ftagPool
    -0.52
    StructEnd
    -0.52
    GraphicsUnit
    -0.52
    ValueStyle
    -0.51
    POSITIVE LOGITS
     EconPapers
    0.58
     [''],
    0.41
     Grecs
    0.37
     felicità
    0.36
     grecque
    0.36
     Água
    0.35
     Dafür
    0.35
     militaires
    0.35
     heller
    0.34
     japonaise
    0.34
    Act Density 0.206%

    No Known Activations