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

    Neuronpedia

    INDEX
    Explanations

    Speculation and stating facts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Что
    -0.07
    Um
    -0.06
    urniture
    -0.06
    'm
    -0.06
     Wh
    -0.06
     Guil
    -0.05
    LECT
    -0.05
     Epoch
    -0.05
     Well
    -0.05
     Parcel
    -0.05
    POSITIVE LOGITS
     مصرف
    0.09
    。これ
    0.07
    _FF
    0.07
    EGIN
    0.07
    fragment
    0.07
     oblasti
    0.07
     서로
    0.07
     Fridays
    0.07
     ﾍ
    0.07
     этому
    0.06
    Act Density 0.180%

    No Known Activations