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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new textual section or a formatting element

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

    Common words ("the", "a", "this", "it")

    np_acts-logits-general · gemini-2.0-flash

    special characters or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.97
    StoryboardSegue
    -0.96
    Билгалдахарш
    -0.96
    Geplaatst
    -0.92
     utafitiHapana
    -0.90
     ProtoMessage
    -0.87
    StandardCharsets
    -0.87
     estimés
    -0.86
    Obrázky
    -0.85
    aarrggbb
    -0.84
    POSITIVE LOGITS
     the
    0.81
     either
    0.57
     a
    0.56
    the
    0.55
     this
    0.54
     it
    0.53
     some
    0.52
    <bos>
    0.52
     them
    0.51
     perhaps
    0.50
    Act Density 0.482%

    No Known Activations