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

    Neuronpedia

    INDEX
    Explanations

    Stages and classifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     https
    -0.09
     लगाने
    -0.08
     omitted
    -0.08
    adge
    -0.08
    కుండా
    -0.08
    _unsigned
    -0.08
     notar
    -0.07
     लगा
    -0.07
    .CASCADE
    -0.07
    Filename
    -0.07
    POSITIVE LOGITS
    人格
    0.09
     characterized
    0.09
    identified
    0.09
     narciss
    0.08
     wɔ
    0.08
     arche
    0.08
     thinkers
    0.08
     прояв
    0.08
    /social
    0.08
     rebels
    0.08
    Act Density 0.020%

    No Known Activations