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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    programming language file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused41>
    -0.95
    ſſung
    -0.95
    <unused1>
    -0.94
    <unused3>
    -0.94
    <unused51>
    -0.94
    <unused52>
    -0.94
    <unused47>
    -0.94
    <unused28>
    -0.94
    <unused11>
    -0.94
    <unused14>
    -0.94
    POSITIVE LOGITS
    .
    0.57
     .
    0.47
    $.
    0.42
    。
    0.41
    ).
    0.36
    *.
    0.35
    ?.
    0.34
    ।
    0.34
    }.
    0.34
    _.
    0.33
    Act Density 0.025%

    No Known Activations