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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    naire
    1.57
    analy
    1.30
    ()["
    1.21
    یمپ
    1.21
     orchestral
    1.19
    ера
    1.18
    ({'
    1.18
    imized
    1.18
    Dru
    1.14
     mononuclear
    1.12
    POSITIVE LOGITS
     साल
    1.22
    हा
    1.21
    まあ
    1.21
    不過
    1.17
     също
    1.17
    ພວກເຮ
    1.14
    イ
    1.12
    ブ
    1.12
    那边
    1.12
    സ
    1.12
    Act Density 0.613%

    No Known Activations