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

    Neuronpedia

    INDEX
    Explanations

    references to functionality and operational issues in code or systems

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

    things that do not work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exactos
    -0.47
     sàng
    -0.44
    issauga
    -0.44
    ztus
    -0.42
     مرئيه
    -0.41
     willingly
    -0.41
     traditionally
    -0.40
    ViewImports
    -0.39
     muestras
    -0.39
    Steady
    -0.39
    POSITIVE LOGITS
    ダメ
    0.52
    だめ
    0.50
     impossible
    0.50
    impossible
    0.50
     useless
    0.50
    useless
    0.50
    imanapun
    0.48
     malfunction
    0.47
     mauvais
    0.47
    sick
    0.47
    Act Density 0.023%

    No Known Activations