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

    Neuronpedia

    INDEX
    Explanations

    Formal/academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    초
    -0.06
    ти
    -0.06
     وی
    -0.06
     fist
    -0.06
    �
    -0.06
    كتور
    -0.06
    ITHER
    -0.06
     DV
    -0.06
     Phát
    -0.06
     dél
    -0.06
    POSITIVE LOGITS
    .Int
    0.07
    _episodes
    0.07
     john
    0.06
    .Intent
    0.06
     Ferdinand
    0.06
     Bluetooth
    0.06
    Liter
    0.06
     mData
    0.06
    .Batch
    0.06
     savedInstanceState
    0.06
    Act Density 0.001%

    No Known Activations