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

    Neuronpedia

    INDEX
    Explanations

    character

    np_max-act · gemini-2.0-flash

    system or runtime error messages (especially SQL/convert error strings) in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    /documentation
    -0.06
     environ
    -0.06
     Tran
    -0.06
     Lifestyle
    -0.06
     Morales
    -0.06
    _dirty
    -0.06
     dbContext
    -0.06
    inputs
    -0.05
    .Headers
    -0.05
     servidor
    -0.05
    POSITIVE LOGITS
     curly
    0.06
     появ
    0.06
    んな
    0.06
     není
    0.06
     allocator
    0.06
    pm
    0.06
     {:?}",
    0.06
     cleric
    0.06
    ｧ
    0.06
    uos
    0.06
    Act Density 0.814%

    No Known Activations