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

    Neuronpedia

    INDEX
    Explanations

    expressions related to guilt and responsibility

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

    motivations and opposing goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.57
     שוליים
    -0.52
     >=",
    -0.50
     Wiktionnaire
    -0.50
    ureusement
    -0.50
    ↹
    -0.49
    Personensuche
    -0.49
     chi̍t
    -0.48
    cionario
    -0.48
    StoryboardSegue
    -0.48
    POSITIVE LOGITS
     Ob
    0.37
     Support
    0.36
     support
    0.36
     fight
    0.35
    KommentareTeilen
    0.33
     đoạn
    0.33
     Batch
    0.33
     ellen
    0.33
     supporting
    0.32
     Grant
    0.32
    Act Density 0.047%

    No Known Activations