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

    Neuronpedia

    INDEX
    Explanations

    specific qualities or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !,
    1.28
    ^{*}$,
    1.20
     ،
    1.20
    $,
    1.20
    $，
    1.19
     !,
    1.19
    并且
    1.15
    ₂,
    1.14
    ="",
    1.13
    **,
    1.13
    POSITIVE LOGITS
     دیا۔
    1.30
    .\\
    1.24
     سکے۔
    1.24
     گئے۔
    1.16
    .\
    1.10
    .
    1.10
    %.
    1.10
    ائیں۔
    1.09
     گیا۔
    1.05
     دی۔
    1.03
    Act Density 0.765%

    No Known Activations