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

    Neuronpedia

    INDEX
    Explanations

    descriptive meaning, condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ayn
    0.46
     temas
    0.45
     कहीं
    0.45
     Hurd
    0.44
     Benefits
    0.43
     त्या
    0.43
     shenanigans
    0.43
     Thema
    0.43
     बढ़ाया
    0.43
     موضوع
    0.42
    POSITIVE LOGITS
    OR
    0.49
    まず
    0.47
    swith
    0.46
    ্প
    0.45
    רה
    0.44
    ί
    0.44
    setWalk
    0.42
    카페
    0.42
    use
    0.42
    ুল
    0.42
    Act Density 0.019%

    No Known Activations