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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بي
    -0.07
    _pid
    -0.07
    Dim
    -0.07
     %@
    -0.06
    _SUCCESS
    -0.06
    纪念馆
    -0.06
    .AbsoluteConstraints
    -0.06
    ⏫
    -0.06
    .HttpSession
    -0.06
     sodium
    -0.06
    POSITIVE LOGITS
     publishing
    0.07
    truck
    0.07
     breaking
    0.07
    起こ
    0.06
    就好
    0.06
     scripts
    0.06
    如果你想
    0.06
     intéress
    0.06
     najb
    0.06
     düşün
    0.06
    Act Density 0.004%

    No Known Activations