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

    Neuronpedia

    INDEX
    Explanations

    reviewed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fet
    -0.07
     CLASS
    -0.07
    Та
    -0.07
    LOOP
    -0.06
     얼
    -0.06
     viene
    -0.06
     Advis
    -0.06
    .OK
    -0.06
     modifiers
    -0.06
     видов
    -0.06
    POSITIVE LOGITS
     оскільки
    0.07
    _um
    0.07
    criteria
    0.06
    dum
    0.06
    Barcode
    0.06
    ��
    0.06
    ourage
    0.06
    "context
    0.06
     plugins
    0.06
     напри
    0.06
    Act Density 0.006%

    No Known Activations