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

    Neuronpedia

    INDEX
    Explanations

    websites and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contradiction
    0.41
     seres
    0.40
     prerog
    0.39
    MsgCallBack
    0.39
     ±
    0.38
     mutable
    0.38
     sıcak
    0.38
    Ṛ
    0.38
     depressions
    0.37
     granule
    0.37
    POSITIVE LOGITS
    ٫
    0.65
    ​.
    0.49
     डॉट
    0.49
    .
    0.49
    www
    0.49
    amazonaws
    0.48
    ‌.
    0.47
    ﹒
    0.47
     www
    0.46
    plus
    0.46
    Act Density 0.039%

    No Known Activations