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

    Neuronpedia

    INDEX
    Explanations

    Automatic

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “automatic” (in any capitalization).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Teil
    -0.07
     rele
    -0.07
    -Life
    -0.07
     Ho
    -0.07
     exploited
    -0.07
     Gre
    -0.07
     Spo
    -0.06
     revenue
    -0.06
     Shade
    -0.06
     den
    -0.06
    POSITIVE LOGITS
     Automatic
    0.09
     automatic
    0.09
    automatic
    0.08
    oman
    0.07
    (!$
    0.07
    自動
    0.07
     attempts
    0.07
     declaration
    0.07
     automat
    0.07
     electrónico
    0.07
    Act Density 0.011%

    No Known Activations