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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific symbols within the text

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

    primarily, mainly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.57
    OGND
    -0.56
    ItemBackground
    -0.49
    bootstrapcdn
    -0.47
    AccessorTable
    -0.45
     تضيفلها
    -0.43
    -0.40
    úgó
    -0.40
    tagHelperRunner
    -0.38
     يتيمه
    -0.38
    POSITIVE LOGITS
     predominantly
    0.52
     primarily
    0.49
    HostException
    0.45
     principalmente
    0.43
    تقاوى
    0.43
     préférence
    0.42
     predomin
    0.42
     mainly
    0.41
    nehm
    0.40
     overwhelmingly
    0.40
    Act Density 0.649%

    No Known Activations