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

    Neuronpedia

    INDEX
    Explanations

    references to knowledge or awareness

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

    志保

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nya
    -0.43
    er
    -0.43
    on
    -0.40
    l
    -0.38
     Korn
    -0.38
     geralmente
    -0.38
    a
    -0.37
    or
    -0.37
    v
    -0.36
    8
    -0.36
    POSITIVE LOGITS
     지
    1.59
    지
    1.48
    知
    1.45
     知
    1.14
     Zhi
    1.13
    Zhi
    1.08
    志
    0.94
    支
    0.88
    지는
    0.87
    지를
    0.86
    Act Density 0.002%

    No Known Activations