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

    Neuronpedia

    INDEX
    Explanations

    guide to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.41
    다
    1.14
    را
    0.95
     Bridge
    0.93
    ↵↵
    0.90
    اج
    0.88
     is
    0.87
    h
    0.86
    tanggal
    0.84
    いを
    0.84
    POSITIVE LOGITS
    0
    1.54
    ０
    1.27
    guide
    1.20
    inę
    1.18
    ᱐
    1.16
    in
    1.15
     ০৯
    1.14
     ০
    1.09
    𝟬
    1.08
    𝟎
    1.05
    Act Density 0.013%

    No Known Activations