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

    Neuronpedia

    INDEX
    Explanations

    Global Interpreter Lock (GIL) limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    я
    0.37
    io
    0.36
    ick
    0.32
    al
    0.32
    की
    0.32
    so
    0.31
    c
    0.29
    nt
    0.29
    imal
    0.29
    ch
    0.28
    POSITIVE LOGITS
     cataly
    0.45
    𝘬
    0.45
    ̴
    0.42
     energetics
    0.42
    病毒
    0.42
     bearers
    0.42
     fooled
    0.42
     antagonists
    0.42
    ⺀
    0.41
    ᴢ
    0.41
    Act Density 0.004%

    No Known Activations