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

    Neuronpedia

    INDEX
    Explanations

    detect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loe
    -0.06
     stemming
    -0.06
    ’я
    -0.06
    'L
    -0.06
    35
    -0.06
    Okay
    -0.06
    يدا
    -0.06
    igor
    -0.06
    乾
    -0.06
    Closed
    -0.06
    POSITIVE LOGITS
     Featured
    0.08
     features
    0.07
    енным
    0.07
     기능
    0.07
    features
    0.07
    ıyı
    0.06
    canvas
    0.06
    .product
    0.06
     #↵↵
    0.06
    �
    0.06
    Act Density 0.034%

    No Known Activations