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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ัก
    -0.07
    τευ
    -0.07
    (always
    -0.07
     推
    -0.07
    ()"↵
    -0.06
     Üy
    -0.06
    .";
↵
    -0.06
     Sorted
    -0.06
    (U
    -0.06
     tertiary
    -0.06
    POSITIVE LOGITS
     worries
    0.06
     sliced
    0.06
    _STACK
    0.06
    自動
    0.06
     rustic
    0.06
    chte
    0.06
    CppGenericClass
    0.06
    ılmaktadır
    0.06
     Legion
    0.06
    983
    0.06
    Act Density 0.096%

    No Known Activations