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

    Neuronpedia

    INDEX
    Explanations

    instances where punctuation and specific conjunctions indicate a new thought or significant transition in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    separating phrases by periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.78
    Билгалдахарш
    -0.60
    LookAnd
    -0.56
    новниш
    -0.52
    tagHelperRunner
    -0.51
     kaarangay
    -0.50
    তথ্যসূত্র
    -0.49
    -0.49
    -0.48
    utives
    -0.46
    POSITIVE LOGITS
    AnimationsModule
    0.39
     efectivamente
    0.38
    FormTagHelper
    0.37
    ########.
    0.35
     venido
    0.35
    unknownFields
    0.35
    XtraGrid
    0.34
     íntegra
    0.34
     entire
    0.33
    ioutil
    0.33
    Act Density 0.074%

    No Known Activations