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

    Neuronpedia

    INDEX
    Explanations

    code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fixtures
    -0.07
    ７
    -0.07
    опри
    -0.07
    下来
    -0.06
     元
    -0.06
     ⌒
    -0.06
     -,
    -0.06
     predicting
    -0.06
     dataset
    -0.06
     haha
    -0.06
    POSITIVE LOGITS
    _house
    0.07
    ENCIL
    0.06
    ciler
    0.06
    (QL
    0.06
     ineffective
    0.06
    	Collection
    0.06
    χεία
    0.06
    MouseButton
    0.06
    τικ
    0.06
    payer
    0.06
    Act Density 0.000%

    No Known Activations