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

    Neuronpedia

    INDEX
    Explanations

    Phangan, plan, authorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bein
    0.38
     बीए
    0.37
    otions
    0.37
    िप
    0.36
     offering
    0.36
     ادار
    0.36
    ⣀
    0.36
     바꾸
    0.35
    ጁ
    0.35
     paise
    0.35
    POSITIVE LOGITS
    マータイヤ
    0.38
     分析
    0.37
    ล็
    0.36
    ༄
    0.36
    筫
    0.36
    ণ্ড
    0.36
     Пере
    0.36
    لوك
    0.36
     Lichtenfels
    0.35
     フロント
    0.35
    Act Density 0.002%

    No Known Activations