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

    Neuronpedia

    INDEX
    Explanations

    elements related to social interactions and gatherings

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

    social groups and friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mess
    -0.38
     Eta
    -0.37
    unknownFields
    -0.36
    msgTypes
    -0.35
     bocca
    -0.35
     pi
    -0.34
    足
    -0.34
     DEL
    -0.34
     SPO
    -0.33
    帆
    -0.33
    POSITIVE LOGITS
     Realität
    0.52
     Grüsse
    0.47
     Freundin
    0.47
    insegna
    0.46
     Fernsehen
    0.45
    Creators
    0.43
     Autorin
    0.43
     Nachbarn
    0.43
     smtplib
    0.43
     kasarigan
    0.42
    Act Density 0.019%

    No Known Activations