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

    Neuronpedia

    INDEX
    Explanations

    performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sd
    -0.08
    ول
    -0.08
     volcanic
    -0.08
    <ll
    -0.08
     fireworks
    -0.07
    ্ৰী
    -0.07
    :path
    -0.07
    .wall
    -0.07
     Autob
    -0.07
     cloak
    -0.07
    POSITIVE LOGITS
    制度
    0.11
     процессе
    0.10
     வருட
    0.10
     систему
    0.09
     annuelle
    0.09
     письмен
    0.09
     appraisal
    0.09
     beoordelingen
    0.09
    /question
    0.08
     nearing
    0.08
    Act Density 0.009%

    No Known Activations