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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اسه
    -0.07
     Hosting
    -0.07
    anners
    -0.07
    TYPE
    -0.07
    intro
    -0.07
    mdb
    -0.06
    WithEmail
    -0.06
    DateString
    -0.06
    elocity
    -0.06
     الكتاب
    -0.06
    POSITIVE LOGITS
     fee
    0.07
    429
    0.06
     constitutional
    0.06
     yum
    0.06
     stom
    0.06
     Es
    0.06
     Nar
    0.06
    ❤
    0.06
    　
    0.06
    040
    0.06
    Act Density 0.012%

    No Known Activations