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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wlan
    -0.06
     будущ
    -0.06
    Lon
    -0.06
     Gray
    -0.06
    Mrs
    -0.06
     ….
    -0.06
    iç
    -0.06
    瓜
    -0.06
     Occup
    -0.06
    (relative
    -0.06
    POSITIVE LOGITS
     còn
    0.07
     이용
    0.07
    资格
    0.07
     appeared
    0.07
    しており
    0.06
    /*!
    0.06
     А
    0.06
     strom
    0.06
    _FORCE
    0.06
    BUG
    0.06
    Act Density 0.013%

    No Known Activations