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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "text" in various forms

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

    patent references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unreasonable
    -0.35
     cappello
    -0.34
     exceeding
    -0.33
    headless
    -0.33
    bi
    -0.33
    major
    -0.33
     ochrony
    -0.32
     lettore
    -0.31
     Nachhal
    -0.31
     fratello
    -0.31
    POSITIVE LOGITS
     Patent
    1.39
     patent
    1.32
    Patent
    1.25
    patent
    1.13
     patents
    0.99
     Patents
    0.98
     PATENT
    0.92
     patente
    0.88
    UserScript
    0.71
     ब्रेकडाउन
    0.70
    Act Density 0.001%

    No Known Activations