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

    Neuronpedia

    INDEX
    Explanations

    minimum and maximum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esto
    -0.07
    _driver
    -0.06
     Warm
    -0.06
    @\
    -0.06
    гот
    -0.06
    Than
    -0.06
     /
    -0.06
    Transactional
    -0.06
    收
    -0.06
    従
    -0.06
    POSITIVE LOGITS
     bergen
    0.07
     europ
    0.07
     Zukunft
    0.06
     황
    0.06
    аксим
    0.06
     dank
    0.06
     Pants
    0.06
     councill
    0.06
     напис
    0.06
     Dumbledore
    0.06
    Act Density 0.009%

    No Known Activations