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

    Neuronpedia

    INDEX
    Explanations

    docstring end */

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phenolic
    0.42
     Bassett
    0.41
     phenols
    0.41
     acide
    0.40
     brisket
    0.39
     Mullen
    0.38
     mucus
    0.38
     degassing
    0.38
     Yakima
    0.37
     basaltes
    0.36
    POSITIVE LOGITS
    */
    1.00
     */
    0.88
    .*/
    0.56
    """
    0.55
    ****************
    0.53
    since
    0.51
    Since
    0.50
    author
    0.49
    -*/
    0.48
    **/
    0.48
    Act Density 0.012%

    No Known Activations