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

    Neuronpedia

    INDEX
    Explanations

    references to specific activities and measurements

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

    activity descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     största
    -0.31
     conclusão
    -0.30
    ultados
    -0.29
     bättre
    -0.29
     valmist
    -0.29
     idéia
    -0.29
     pelanggan
    -0.29
     Käufer
    -0.28
     Entste
    -0.28
     Mannschaft
    -0.28
    POSITIVE LOGITS
     Activities
    1.59
    Activities
    1.57
     activities
    1.56
     activity
    1.52
     Activity
    1.49
    activities
    1.49
     ACTIVITIES
    1.43
    Activity
    1.41
    activity
    1.37
     ACTIVITY
    1.30
    Act Density 0.064%

    No Known Activations