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

    Neuronpedia

    INDEX
    Explanations

    elements related to formal statements and their accompanying details

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

    Ends with end_of_turn token

    np_acts-logits-general · gemini-2.0-flash

    end of phrase/sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.71
    HideFlags
    -0.70
    tagHelperRunner
    -0.69
     ſind
    -0.67
     jspb
    -0.65
    Jeografia
    -0.65
    хьтан
    -0.65
     &___
    -0.63
    -------------</
    -0.63
    ittarius
    -0.61
    POSITIVE LOGITS
     mesma
    0.38
     same
    0.35
     ucapnya
    0.31
     parro
    0.30
    same
    0.30
    还要
    0.30
     mismo
    0.29
    owiec
    0.29
     echo
    0.28
    Same
    0.28
    Act Density 0.899%

    No Known Activations