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

    Neuronpedia

    INDEX
    Explanations

    geometry and transformers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eggs
    -0.08
     Eggs
    -0.08
     natürlich
    -0.08
     मतलब
    -0.08
    egg
    -0.08
    spawn
    -0.08
    Egg
    -0.07
     mayonnaise
    -0.07
     dice
    -0.07
    (","
    -0.07
    POSITIVE LOGITS
     Wach
    0.08
     tuner
    0.08
     עליו
    0.08
     kok
    0.08
     литера
    0.07
     Guia
    0.07
     lit
    0.07
     некоторое
    0.07
    ા�
    0.07
     uphill
    0.07
    Act Density 0.001%

    No Known Activations