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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GreaterThan
    -0.06
    otyping
    -0.06
    .raise
    -0.06
     Py
    -0.06
     보면
    -0.06
     modulation
    -0.06
     mesure
    -0.06
    gray
    -0.06
    ("%.
    -0.06
     tails
    -0.06
    POSITIVE LOGITS
    уч
    0.08
    Common
    0.07
     Fighter
    0.07
    enzie
    0.06
     значительно
    0.06
    ennial
    0.06
     shopper
    0.06
    γχ
    0.06
    ".$
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Act Density 0.008%

    No Known Activations