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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and the beginning of sentences

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

    historical French words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.48
     magical
    -0.41
    oms
    -0.40
     fairy
    -0.40
     للاسماء
    -0.39
     mud
    -0.39
    hod
    -0.39
    odzi
    -0.38
     ups
    -0.38
     poison
    -0.38
    POSITIVE LOGITS
     auroit
    0.64
     étoient
    0.62
     feroit
    0.61
     avoient
    0.60
     enfans
    0.59
     âmes
    0.55
     prêtres
    0.55
    enumii
    0.54
     étoit
    0.54
     pouvoit
    0.54
    Act Density 0.000%

    No Known Activations