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

    Neuronpedia

    INDEX
    Explanations

    contractions and negations in the text

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

    can't VERB inability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.49
    errHandler
    -0.49
     الرياضيه
    -0.45
    bosis
    -0.44
    usitis
    -0.44
    IUrlHelper
    -0.44
    kran
    -0.43
    addContainerGap
    -0.42
    mallow
    -0.42
     ap
    -0.40
    POSITIVE LOGITS
    ьаж
    0.47
    Ƚ
    0.47
     виправивши
    0.44
     Réponses
    0.43
    Kelebihan
    0.42
    AddTagHelper
    0.41
    SequentialGroup
    0.40
     didalam
    0.40
    OrNil
    0.40
    وانید
    0.39
    Act Density 0.014%

    No Known Activations