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

    Neuronpedia

    INDEX
    Explanations

    LaTeX mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    -3.11
    1
    -3.03
    4
    -2.86
    ８
    -2.72
    Tempat
    -2.72
    Two
    -2.64
    辚
    -2.63
    7
    -2.55
    ５
    -2.55
    Pendidikan
    -2.47
    POSITIVE LOGITS
    y
    3.19
    </h3>
    3.13
    re
    3.08
    e
    3.05
    in
    3.03
    </strong>
    3.03
    al
    2.98
    te
    2.88
    h
    2.86
    ra
    2.80
    Act Density 0.004%

    No Known Activations