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

    Neuronpedia

    INDEX
    Explanations

    List, question, and phrase structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    觡
    0.47
    觛
    0.46
    䆔
    0.45
    嬂
    0.44
    䂘
    0.43
    𝚈
    0.43
     popolare
    0.42
    枞
    0.42
    攺
    0.42
     regia
    0.41
    POSITIVE LOGITS
     Azure
    0.41
     keyboard
    0.40
    Message
    0.39
     benchmark
    0.39
    Map
    0.39
    px
    0.38
    List
    0.38
     (
    0.37
     face
    0.36
    Nelson
    0.36
    Act Density 0.000%

    No Known Activations