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

    Neuronpedia

    INDEX
    Explanations

    Vari

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DELETE
    -0.07
     Sel
    -0.07
    Account
    -0.07
    ровать
    -0.07
    Invoke
    -0.07
     spins
    -0.07
    773
    -0.07
     filed
    -0.07
     negligent
    -0.07
     října
    -0.06
    POSITIVE LOGITS
    thood
    0.07
     그를
    0.07
     phụ
    0.07
    興
    0.06
    اسة
    0.06
     عقد
    0.06
     ประเภท
    0.06
     وضع
    0.06
     stripslashes
    0.06
     Phonetic
    0.06
    Act Density 0.002%

    No Known Activations