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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tuần
    -0.06
    ++;↵
    -0.06
     Dag
    -0.06
    vil
    -0.06
    ять
    -0.06
    äche
    -0.06
    applicant
    -0.06
     Django
    -0.06
     convex
    -0.06
     Dexter
    -0.06
    POSITIVE LOGITS
    _LA
    0.07
    {lng
    0.07
     photos
    0.06
    蘭
    0.06
    -non
    0.06
     richt
    0.06
    嘛
    0.06
    isempty
    0.06
    -progress
    0.06
    141
    0.06
    Act Density 0.003%

    No Known Activations