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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signify the end of sentences

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

    numbers, periods, and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arangay
    -0.71
    征詢我
    -0.70
     ſei
    -0.69
    niſſe
    -0.69
    <unused41>
    -0.69
    <unused42>
    -0.68
    phazard
    -0.68
    <unused23>
    -0.68
    [@BOS@]
    -0.68
    <unused1>
    -0.68
    POSITIVE LOGITS
    .
    0.51
    item
    0.46
    :
    0.43
    *
    0.42
    subsection
    0.41
    دانشنامهٔ
    0.40
    '.
    0.39
    </tr>
    0.38
    *.
    0.38
     noDo
    0.37
    Act Density 0.106%

    No Known Activations