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

    Neuronpedia

    INDEX
    Explanations

    Allies and cooperation

    np_max-act · gemini-2.0-flash

    This neuron fires on sentence-initial transition words or phrases (e.g. But, Now, Along, As, With, However) that signal narrative shifts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Stard
    -0.07
    nitř
    -0.07
     коштів
    -0.07
    488
    -0.07
    William
    -0.07
    .↵↵↵↵
    -0.06
     pronunciation
    -0.06
     postage
    -0.06
     treasure
    -0.06
     calculator
    -0.06
    POSITIVE LOGITS
     UCS
    0.07
    .groupControl
    0.06
     lez
    0.06
    ульта
    0.06
     капіт
    0.06
    (stdin
    0.06
    -coordinate
    0.06
    empor
    0.06
    (Guid
    0.06
     Denise
    0.06
    Act Density 0.049%

    No Known Activations