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

    Neuronpedia

    INDEX
    Explanations

    temperature ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AppModule
    0.39
     unwarrant
    0.38
     Вайлд
    0.38
    ﻅ
    0.38
    Roots
    0.38
    訒
    0.38
    도의
    0.37
    溘
    0.36
    গণের
    0.36
    ToIndex
    0.36
    POSITIVE LOGITS
     (“
    0.42
    烷
    0.40
     last
    0.40
    WebServer
    0.40
    last
    0.40
     dart
    0.40
     padding
    0.38
     “
    0.38
     chevron
    0.38
     dig
    0.38
    Act Density 0.000%

    No Known Activations