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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विस्तृत
    0.49
    āda
    0.46
    eve
    0.44
    阡
    0.44
    edown
    0.43
    寰
    0.43
    シー
    0.41
    clarinet
    0.41
     მთ
    0.41
     Ā
    0.41
    POSITIVE LOGITS
    q
    0.52
    м
    0.51
     syncing
    0.47
    عرف
    0.46
    m
    0.45
    ync
    0.44
    Programs
    0.43
     auto
    0.42
     automatically
    0.42
    wm
    0.42
    Act Density 0.000%

    No Known Activations