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

    Neuronpedia

    INDEX
    Explanations

    inquiries about comparative analysis and causal relationships

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

    How something affects/influences something else

    np_acts-logits-general · gemini-2.0-flash

    how things relate and change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sedia
    -0.54
    strongly
    -0.51
     strongly
    -0.48
     sérieux
    -0.47
    certainly
    -0.47
     fortement
    -0.47
    +#+
    -0.45
     complètes
    -0.44
     certainly
    -0.43
     unquestionably
    -0.42
    POSITIVE LOGITS
     compares
    1.04
     relates
    1.04
     affects
    1.04
     differs
    1.03
     relate
    1.03
     affect
    0.98
     interacts
    0.94
     compare
    0.91
     differ
    0.91
     interact
    0.90
    Act Density 0.177%

    No Known Activations