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

    Neuronpedia

    INDEX
    Explanations

    references to fictional characters and technical terms related to programming and games

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

    Jedi words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OPPO
    -0.62
     للاسماء
    -0.59
     Corinne
    -0.57
    ourke
    -0.55
     Bursa
    -0.52
     Coimbatore
    -0.52
    icoot
    -0.51
    -0.51
     Antalya
    -0.50
    SPO
    -0.50
    POSITIVE LOGITS
    Jedis
    1.21
     jedis
    1.02
    jedis
    1.01
     Jed
    0.89
    Jed
    0.78
     Jedi
    0.67
    Jedi
    0.66
    jed
    0.66
     jed
    0.65
     Jes
    0.59
    Act Density 0.001%

    No Known Activations