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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     current
    -0.06
     Speakers
    -0.06
     quiero
    -0.06
     Seat
    -0.06
     Guys
    -0.06
     trailer
    -0.06
     resp
    -0.06
     carriers
    -0.06
     나타
    -0.06
     Ulus
    -0.06
    POSITIVE LOGITS
    Finite
    0.07
    ikip
    0.06
    ’deki
    0.06
    ://{
    0.06
    едак
    0.06
     �
    0.06
    _DIRECTION
    0.06
    _that
    0.06
     Sequence
    0.06
    ทร
    0.06
    Act Density 0.000%

    No Known Activations