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

    Neuronpedia

    INDEX
    Explanations

    ’s

    np_max-act · gemini-2.0-flash

    This neuron consistently activates on the first content word at the start of a new text segment (or paragraph), marking the beginning of passages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Appointment
    -0.07
    [OF
    -0.06
    processors
    -0.06
    |^
    -0.06
     Odkazy
    -0.06
     pwd
    -0.06
    cie
    -0.06
     subdir
    -0.06
     Velvet
    -0.06
     thưởng
    -0.06
    POSITIVE LOGITS
     <↵
    0.07
    inaire
    0.07
    ’elle
    0.07
     trib
    0.07
     صنایع
    0.07
     Indicates
    0.06
    (parent
    0.06
     Corporation
    0.06
    :A
    0.06
     CSS
    0.06
    Act Density 0.046%

    No Known Activations