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

    Neuronpedia

    INDEX
    Explanations

    common words and phrases that indicate requests or clarifications in communication

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

    if.

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ItemSelected
    -0.51
    tonsoft
    -0.50
     Audiodateien
    -0.48
     AttributeSet
    -0.47
    moveToFirst
    -0.46
    뀐
    -0.45
    ChildScrollView
    -0.45
    setof
    -0.44
    AdapterView
    -0.44
    fromCharCode
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.44
    الحياه
    0.44
     might
    0.40
     Bonif
    0.39
     probably
    0.38
     will
    0.36
    Acab
    0.35
     CanadaChoose
    0.35
     sẽ
    0.35
     볼
    0.35
    Act Density 0.124%

    No Known Activations