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

    Neuronpedia

    INDEX
    Explanations

    programming principles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tout
    -0.07
     Winning
    -0.07
    сты
    -0.07
     Tanzania
    -0.06
     Pil
    -0.06
     Nah
    -0.06
     nouvelles
    -0.06
     Pasta
    -0.06
     XVI
    -0.06
    interpreted
    -0.06
    POSITIVE LOGITS
    DidAppear
    0.07
    >Email
    0.06
    限定
    0.06
    .Track
    0.06
     generalize
    0.06
    textView
    0.06
     giants
    0.06
    े
    0.06
     Π
    0.06
    enheim
    0.06
    Act Density 0.019%

    No Known Activations