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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sau
    -0.07
     saldırı
    -0.07
     recognizer
    -0.07
    (issue
    -0.07
    accounts
    -0.06
     success
    -0.06
    Ins
    -0.06
    _btn
    -0.06
    interaction
    -0.06
    Listing
    -0.06
    POSITIVE LOGITS
    processable
    0.06
     Persian
    0.06
     инт
    0.06
    ("&
    0.06
    بت
    0.06
     Export
    0.06
    اورزی
    0.06
    pit
    0.06
     "&
    0.06
     opat
    0.06
    Act Density 0.068%

    No Known Activations