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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to significant themes or objects in narratives

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

    describing something as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.37
    Tru
    -0.35
    konos
    -0.33
    ATTN
    -0.33
    ?><
    -0.32
     Pok
    -0.31
     rites
    -0.30
    crest
    -0.30
    PAP
    -0.30
     PLA
    -0.29
    POSITIVE LOGITS
    utilisons
    0.65
    RTLU
    0.64
    XMLSchema
    0.63
     autorytatywna
    0.60
    ValueGeneration
    0.60
     contextLoads
    0.58
    writeFieldEnd
    0.57
     wireType
    0.57
     indígen
    0.57
     Audiodateien
    0.56
    Act Density 0.362%

    No Known Activations