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

    Neuronpedia

    INDEX
    Explanations

    Sneaker, responsibility, Ketene

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    taxonomy
    0.39
     বৌদ্ধ
    0.37
     Aik
    0.36
    ʹ
    0.36
    ケン
    0.35
     Telef
    0.35
     संकल्प
    0.34
     Admissions
    0.34
     Pek
    0.34
     جغ
    0.34
    POSITIVE LOGITS
    रोज
    0.41
    चलित
    0.40
    ৯০
    0.39
     finalist
    0.38
     distract
    0.37
     இறுதியில்
    0.36
    స్తే
    0.35
    রিদ্র
    0.35
    に向
    0.35
    ющую
    0.35
    Act Density 0.041%

    No Known Activations