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

    Neuronpedia

    INDEX
    Explanations

    below

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “below” (as used in legal texts to refer back to parties or sections).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,ch
    -0.07
     treating
    -0.06
    -edge
    -0.06
    casting
    -0.06
    imeline
    -0.06
    /of
    -0.06
    .Insert
    -0.06
    ffee
    -0.06
    бов
    -0.06
    ुल
    -0.06
    POSITIVE LOGITS
     task
    0.07
     NEED
    0.07
     наш
    0.06
     확실
    0.06
     vie
    0.06
     rq
    0.06
    (non
    0.06
     RowBox
    0.06
    0.06
     Wanted
    0.06
    Act Density 0.002%

    No Known Activations