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

    Neuronpedia

    INDEX
    Explanations

    having followed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    های
    1.30
    ก
    1.28
    ।
    1.11
    т
    1.09
    。
    1.02
    나
    1.00
    ።
    0.99
     rằng
    0.96
    。(
    0.96
    。<
    0.95
    POSITIVE LOGITS
    Having
    1.45
     having
    1.32
    having
    1.29
    し
    1.27
    it
    1.24
     Having
    1.22
    ra
    1.20
    ول
    1.20
    u
    1.12
    و
    1.09
    Act Density 0.011%

    No Known Activations