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

    Neuronpedia

    INDEX
    Explanations

    negations or words indicating denial

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

    negation or failure, in multiple languages

    np_acts-logits-general · gemini-2.0-flash

    não entiendo, je ne comprend pas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     satunya
    -0.67
     ++)
    -0.62
    stdc
    -0.58
     zufolge
    -0.56
    忑
    -0.56
    GOTREF
    -0.55
    opcional
    -0.55
    still
    -0.55
     интен
    -0.54
     ++;
    -0.53
    POSITIVE LOGITS
    expandindo
    0.78
    InvalidProtocol
    0.65
    saraba
    0.58
     وصلة
    0.56
    cadilly
    0.53
    AntiForgeryToken
    0.53
    rachtet
    0.53
    featureID
    0.52
    ClientSize
    0.52
    تقاوى
    0.51
    Act Density 0.052%

    No Known Activations