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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions and analyses of findings or results in research

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

    Follows verbs of discovery/identification

    np_acts-logits-general · gemini-2.0-flash

    finding or revealing results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.68
     fubject
    -0.53
    extAlignment
    -0.51
    isSuccessful
    -0.50
     Sơ
    -0.50
    setVerticalGroup
    -0.49
     Houſe
    -0.48
     Winaray
    -0.48
    acteria
    -0.46
     contextLoads
    -0.46
    POSITIVE LOGITS
     bleek
    0.41
    みると
    0.40
     blijkt
    0.39
    无
    0.38
    SourceChecksum
    0.38
    發現
    0.36
    发现
    0.36
     thấy
    0.36
     okaza
    0.36
     amazed
    0.35
    Act Density 0.816%

    No Known Activations