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

    Neuronpedia

    INDEX
    Explanations

    negations and negative expressions

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

    Follows negations or negative polarity items in multiple languages

    np_acts-logits-general · gemini-2.0-flash

    negation in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eszköz
    -0.47
     epistle
    -0.47
     downstream
    -0.46
    jacent
    -0.45
     régi
    -0.45
    ​
    -0.45
    ลักษ
    -0.45
     liberated
    -0.45
     meeste
    -0.44
     eventualmente
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.78
    الحياه
    0.78
    CppMethod
    0.76
     rospy
    0.74
    aarrggbb
    0.74
    bewerken
    0.74
     defaultstate
    0.73
    +#+#
    0.72
    apimachinery
    0.71
     صوتيه
    0.70
    Act Density 0.042%

    No Known Activations