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

    Neuronpedia

    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Entry
    -0.07
     Range
    -0.07
    look
    -0.07
     legalization
    -0.06
     judged
    -0.06
     jclass
    -0.06
    seen
    -0.06
    _range
    -0.06
     Sentence
    -0.06
    661
    -0.06
    POSITIVE LOGITS
     informatie
    0.07
     Российской
    0.07
    보았다
    0.07
    .AutoField
    0.07
    .profile
    0.07
    ंद
    0.07
     проф
    0.07
     provided
    0.07
     refin
    0.07
     inşa
    0.06
    Act Density 0.019%

    No Known Activations