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

    Neuronpedia

    INDEX
    Explanations

    clips queen mattress signal spots TruthfulQA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    which
    0.53
     SWIM
    0.49
    ซึ่ง
    0.48
    where
    0.48
    bike
    0.47
    tips
    0.47
     which
    0.47
    ت
    0.46
    ่
    0.46
    و
    0.46
    POSITIVE LOGITS
    θηκαν
    0.57
    θηκε
    0.52
     dieron
    0.50
    óln
    0.49
     каса
    0.48
     матери
    0.46
     كات
    0.46
    ються
    0.46
     τραγ
    0.45
    ार्टम
    0.45
    Act Density 0.000%

    No Known Activations