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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conse
    -0.07
     ep
    -0.06
    (RE
    -0.06
    _frames
    -0.06
    飛
    -0.06
    _CONSTANT
    -0.06
     RAW
    -0.06
     συνέ
    -0.06
     Foam
    -0.06
    (gr
    -0.06
    POSITIVE LOGITS
     eles
    0.07
     ribbon
    0.07
    lectric
    0.06
    -dark
    0.06
    _repository
    0.06
     properly
    0.06
    도로
    0.06
    'LBL
    0.06
     Effective
    0.06
     unacceptable
    0.06
    Act Density 0.000%

    No Known Activations