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

    Neuronpedia

    INDEX
    Explanations

    specific sequences or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Streams
    0.42
    ENTES
    0.41
    нес
    0.40
     산
    0.39
     Streaming
    0.39
    ించి
    0.38
     arc
    0.38
     connaît
    0.38
    凹
    0.38
     архівної
    0.38
    POSITIVE LOGITS
     beasts
    0.43
     baseApiPath
    0.42
    ಹಿತ
    0.41
    ┎
    0.40
     revelation
    0.39
    niger
    0.38
    。。
    0.38
    Becker
    0.38
     مدی
    0.37
     medica
    0.37
    Act Density 0.002%

    No Known Activations