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

    Neuronpedia

    INDEX
    Explanations

    comprehension separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    timeouts
    -0.08
     رنگ
    -0.08
    -transparent
    -0.08
    'at
    -0.07
     रोल
    -0.07
     çöz
    -0.07
    ateko
    -0.07
     شا
    -0.07
    še
    -0.07
     لید
    -0.07
    POSITIVE LOGITS
    _configuration
    0.08
    _average
    0.07
    al
    0.07
     fu
    0.07
    _extension
    0.07
    але
    0.07
     prazer
    0.07
     privaten
    0.07
    _generic
    0.07
    aley
    0.07
    Act Density 0.000%

    No Known Activations