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

    Neuronpedia

    INDEX
    Explanations

    negations or negative expressions

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

    ne ... not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.53
    Portail
    -0.50
    /**
    -0.50
     Parkway
    -0.47
    endregion
    -0.47
    ↪
    -0.46
    ruptedException
    -0.46
    مصادر
    -0.45
     ब्रेकडाउन
    -0.45
     Tapatalk
    -0.44
    POSITIVE LOGITS
     only
    0.60
     never
    0.60
     chỉ
    0.59
    DoNot
    0.56
     hanya
    0.56
     nevy
    0.56
     Never
    0.56
     NEVER
    0.53
     Chỉ
    0.53
     لا
    0.52
    Act Density 0.006%

    No Known Activations