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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and other separators

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

    Rick Anwar shoot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FileList
    -0.48
     ſta
    -0.46
    <bos>
    -0.44
    entityId
    -0.41
    toHaveBeenCalled
    -0.40
     equipment
    -0.37
    nativeElement
    -0.37
    ‍
    -0.37
     houſe
    -0.36
     ElementRef
    -0.36
    POSITIVE LOGITS
    iarkan
    0.69
    بوابة
    0.64
     reír
    0.62
     InputDecoration
    0.62
     Económica
    0.61
    esinde
    0.60
    )、
    0.60
     ayrıca
    0.59
     따라
    0.58
    الحياه
    0.57
    Act Density 0.001%

    No Known Activations