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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wo
    -0.07
     通
    -0.06
    DWORD
    -0.06
     Mazda
    -0.06
    Deck
    -0.06
    hop
    -0.06
     少
    -0.06
     Saved
    -0.06
     обязан
    -0.06
     Encryption
    -0.06
    POSITIVE LOGITS
    <>(
    0.07
     NotImplemented
    0.07
     alas
    0.07
     февраля
    0.07
     knih
    0.06
     props
    0.06
    　
    0.06
     развитие
    0.06
     treasure
    0.06
     treasures
    0.06
    Act Density 0.032%

    No Known Activations