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

    Neuronpedia

    INDEX
    Explanations

    flavor Log

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OID
    0.42
    ุป
    0.39
    絢
    0.38
    财经
    0.37
    蹊
    0.36
     False
    0.35
    <0xE4>
    0.34
     geometric
    0.34
     عش
    0.34
    ]]$
    0.34
    POSITIVE LOGITS
    LoggerFactory
    0.73
     LoggerFactory
    0.58
    forcements
    0.42
    拏
    0.42
    IL
    0.39
     Loki
    0.38
    Marker
    0.38
    TGF
    0.38
     அற்புத
    0.38
     ಉತ್
    0.38
    Act Density 0.000%

    No Known Activations