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

    Neuronpedia

    INDEX
    Explanations

    Castings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uz
    0.39
     primero
    0.39
    ano
    0.38
    firstname
    0.37
    ala
    0.37
    nda
    0.37
     Primero
    0.36
    month
    0.36
    kk
    0.36
    inski
    0.36
    POSITIVE LOGITS
     sırasında
    0.42
    Resolved
    0.40
     internally
    0.39
    Ongoing
    0.39
    Context
    0.38
     گیری
    0.38
     ڪرڻ
    0.38
     spineItem
    0.38
    Intern
    0.38
     callback
    0.37
    Act Density 0.013%

    No Known Activations