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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects ordinal ranking phrases (e.g. “first,” “second,” “sixth,” “youngest,” “highest”) that mark superlative or record-setting mentions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ButtonDown
    -0.06
    /cal
    -0.06
     mischief
    -0.06
     mit
    -0.06
    -ag
    -0.06
     Cal
    -0.06
     دوب
    -0.06
     tal
    -0.06
     Sevent
    -0.06
     мех
    -0.06
    POSITIVE LOGITS
     zby
    0.07
    drawing
    0.07
     currentPage
    0.07
    Did
    0.06
    willReturn
    0.06
    (check
    0.06
     obvyk
    0.06
    ımızın
    0.06
    Breaking
    0.06
    Visit
    0.06
    Act Density 0.008%

    No Known Activations