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

    Neuronpedia

    INDEX
    Explanations

    opera

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gradient
    -0.10
    fitness
    -0.09
    gradient
    -0.08
    riend
    -0.08
     Gradient
    -0.08
     منش
    -0.08
    .friend
    -0.08
     gradients
    -0.08
    _gradient
    -0.08
    RIEND
    -0.08
    POSITIVE LOGITS
     kaal
    0.09
     pros
    0.09
    Format
    0.08
     puppet
    0.08
    戏
    0.08
    _format
    0.08
     расска
    0.08
     cae
    0.08
     hut
    0.08
    Explain
    0.08
    Act Density 0.004%

    No Known Activations