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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (branch
    -0.07
    iek
    -0.06
     THIRD
    -0.06
    ','"+
    -0.06
    |.
    -0.06
     وس
    -0.06
     difer
    -0.06
    _In
    -0.06
     consulate
    -0.06
    need
    -0.06
    POSITIVE LOGITS
    �
    0.06
    sure
    0.06
    잔
    0.06
    usercontent
    0.06
     documentation
    0.06
     -(
    0.06
     боя
    0.06
    Nano
    0.06
    _extraction
    0.06
     palette
    0.06
    Act Density 0.013%

    No Known Activations