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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artment
    -0.08
     극
    -0.07
    /pay
    -0.06
    اب
    -0.06
     chữa
    -0.06
    δυ
    -0.06
    (savedInstanceState
    -0.06
    segment
    -0.06
     mamma
    -0.06
    ьи
    -0.06
    POSITIVE LOGITS
    })↵
    0.06
    (history
    0.06
    …↵↵
    0.06
     …↵
    0.06
     exhausted
    0.06
     fiyat
    0.06
     xv
    0.06
     ToString
    0.06
     Servers
    0.06
     cuda
    0.06
    Act Density 0.043%

    No Known Activations