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

    Neuronpedia

    INDEX
    Explanations

    in / on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    의
    0.23
    ⓡ,
    0.22
    ‌های
    0.21
    の
    0.21
    <unused2197>
    0.21
    দের
    0.21
    Brick
    0.20
    醬
    0.20
    찧
    0.20
    }</
    0.19
    POSITIVE LOGITS
     vissa
    0.23
     Расійскай
    0.23
     contrary
    0.22
     cui
    0.21
     realidad
    0.21
     situations
    0.21
     réalité
    0.21
     промышленности
    0.21
     sammen
    0.21
     Linux
    0.20
    Act Density 0.073%

    No Known Activations