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

    Neuronpedia

    INDEX
    Explanations

    references to book clubs and related discussions

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

    discussion questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.52
    ftagPool
    -0.51
    rschein
    -0.47
     continúas
    -0.44
     impreso
    -0.43
    isamment
    -0.43
    ActionCreators
    -0.43
    Introduced
    -0.42
     carrots
    -0.40
     garages
    -0.40
    POSITIVE LOGITS
    Билгалдахарш
    0.48
    rrggbb
    0.40
    unmodifiable
    0.39
    kuuta
    0.36
    Hochspringen
    0.34
    あらすじ
    0.34
    ضير
    0.33
     Signalez
    0.32
     spoiler
    0.32
     uLocal
    0.32
    Act Density 0.205%

    No Known Activations