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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nym
    -0.07
     अर
    -0.07
     }>
    -0.07
     خو
    -0.07
    _MEMORY
    -0.07
    361
    -0.07
    .FileWriter
    -0.06
    359
    -0.06
    rites
    -0.06
    お
    -0.06
    POSITIVE LOGITS
    |
    0.07
     |
    0.07
    """
↵
↵
    0.07
    IGHT
    0.07
    .|
    0.06
    -mort
    0.06
    enze
    0.06
    ôme
    0.06
    */
↵
↵
    0.06
    )|
    0.06
    Act Density 0.015%

    No Known Activations