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

    Neuronpedia

    INDEX
    Explanations

    infinitely, one, repeated, coincident

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ltd
    0.40
     expedit
    0.40
    bgColor
    0.40
     Hugo
    0.39
     oficialmente
    0.38
     Hỏi
    0.38
     Upload
    0.38
     عط
    0.38
     η
    0.38
     वैक्सी
    0.38
    POSITIVE LOGITS
    INFIN
    0.40
     圆
    0.38
    ๓
    0.37
     совершен
    0.37
    越来越
    0.36
    Conference
    0.36
     చేరు
    0.36
    셨
    0.36
     toeg
    0.35
    ยิ่ง
    0.35
    Act Density 0.001%

    No Known Activations