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

    Neuronpedia

    INDEX
    Explanations

    algebraic equations, simplifying expressions, variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    og
    1.22
    at
    1.21
    c
    1.20
     on
    1.20
    ang
    1.18
    g
    1.14
    os
    1.13
    ke
    1.08
    y
    1.08
    1
    1.06
    POSITIVE LOGITS
     Algebra
    1.17
    ０
    1.02
    𝟎
    1.01
    ૦
    0.98
     algebra
    0.95
    ۰
    0.95
    ั
    0.94
    ୦
    0.91
    டுத்த
    0.90
    ্প
    0.89
    Act Density 0.003%

    No Known Activations