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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vapor
    -0.06
     ADA
    -0.06
     Parking
    -0.06
    ування
    -0.06
    zych
    -0.06
    構
    -0.06
    ستان
    -0.06
     які
    -0.06
    "]]
    -0.06
     symb
    -0.06
    POSITIVE LOGITS
     cellular
    0.07
    خط
    0.07
    vailable
    0.07
    caret
    0.07
     Гри
    0.06
    .hw
    0.06
     discret
    0.06
    ,True
    0.06
     edilmiş
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations