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

    Neuronpedia

    INDEX
    Explanations

    operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    야
    2.64
    stackpath
    2.61
    seekg
    2.55
    м
    2.33
     carg
    2.33
     ليصل
    2.32
    ς
    2.28
     vx
    2.25
     oversight
    2.22
     cov
    2.19
    POSITIVE LOGITS
     Başkan
    2.97
    க
    2.95
    ervlak
    2.95
    liness
    2.83
    いない
    2.73
    stuffs
    2.69
     Fakat
    2.60
     diathermy
    2.56
    skar
    2.56
    lacian
    2.55
    Act Density 0.335%

    No Known Activations