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
    舍
    -0.07
     persever
    -0.06
     codecs
    -0.06
    explo
    -0.06
    	flags
    -0.06
     město
    -0.06
    _validate
    -0.06
     moll
    -0.06
    ीप
    -0.06
    Ek
    -0.06
    POSITIVE LOGITS
     REALLY
    0.07
    _TODO
    0.06
    asdf
    0.06
     dozens
    0.06
     nonsense
    0.06
     etm
    0.06
    .getDocument
    0.06
     py
    0.06
     bạn
    0.06
    DEN
    0.06
    Act Density 0.042%

    No Known Activations