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

    Neuronpedia

    INDEX
    Explanations

    letters and spelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CHILD
    -0.07
    owego
    -0.07
     RIGHT
    -0.06
     GROUP
    -0.06
    _Frame
    -0.06
     teb
    -0.06
    _validator
    -0.06
     sergeant
    -0.06
    ksiyon
    -0.06
    -facebook
    -0.06
    POSITIVE LOGITS
    ленні
    0.06
     процессе
    0.06
    输
    0.06
    Ticker
    0.06
     ‏
    0.06
     inefficient
    0.06
     preached
    0.06
     decipher
    0.06
     intertw
    0.06
    substr
    0.06
    Act Density 0.011%

    No Known Activations