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

    Neuronpedia

    INDEX
    Explanations

    expired, ellipse, or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     homomorphism
    1.17
     absorb
    1.16
    ULAR
    1.16
    <unused461>
    1.13
     обычно
    1.09
     Labrenzia
    1.07
     пределах
    1.06
     cư
    1.05
    сона
    1.04
     왕
    1.03
    POSITIVE LOGITS
    s
    1.18
    आपने
    1.01
    e
    1.01
    ा
    1.00
    Andrews
    0.99
    as
    0.97
    Exit
    0.93
    gung
    0.93
    ား
    0.93
    ের
    0.92
    Act Density 0.001%

    No Known Activations