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

    Neuronpedia

    INDEX
    Explanations

    Gemma model, PM, valley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᙱ
    0.53
     TestAvg
    0.50
     पारंपरिक
    0.48
     civile
    0.47
     설치
    0.47
     Heller
    0.47
    นั้น
    0.46
     Januari
    0.46
     timescale
    0.46
     Soldiers
    0.45
    POSITIVE LOGITS
    r
    0.59
    i
    0.49
    z
    0.47
     engulfed
    0.44
    भोपाल
    0.44
    bott
    0.44
     ensured
    0.43
    gem
    0.43
    t
    0.43
     allong
    0.42
    Act Density 0.001%

    No Known Activations