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

    Neuronpedia

    INDEX
    Explanations

    foreign characters or scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    1.28
     peac
    1.18
    "}
    1.16
    ム
    1.11
    ng
    1.08
    Removed
    1.07
    Fon
    1.06
    "(
    1.06
     দীর্ঘদিন
    1.05
    ফ
    1.05
    POSITIVE LOGITS
     hep
    1.08
     spoilt
    1.05
     лиш
    1.04
     আও
    1.03
     verts
    1.02
     Fasc
    1.02
    დება
    1.01
     showdown
    1.01
     delet
    1.01
    ็ด
    1.01
    Act Density 0.000%

    No Known Activations