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

    Neuronpedia

    INDEX
    Explanations

    scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रोगियों
    0.38
    නි
    0.37
    廸
    0.36
     didSet
    0.35
    omegran
    0.35
    耺
    0.34
     आतंकियों
    0.34
     déput
    0.34
    مي
    0.33
    wab
    0.33
    POSITIVE LOGITS
     випад
    0.42
     হলো
    0.42
     apostila
    0.39
    ático
    0.38
    就是
    0.37
     commitments
    0.37
     fich
    0.37
    анд
    0.37
     señ
    0.37
    בה
    0.37
    Act Density 0.004%

    No Known Activations