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

    Neuronpedia

    INDEX
    Explanations

    rhyming words or sentences ending with prompt word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \)
    0.70
     ],
    0.67
    0.66
     },
    0.65
     einen
    0.62
     """
    0.62
     */
    0.61
     Ca
    0.58
     main
    0.58
     sự
    0.57
    POSITIVE LOGITS
    Nope
    0.81
    ЕС
    0.79
    ють
    0.79
    Př
    0.79
    Además
    0.78
    Blurred
    0.78
    MAE
    0.78
    But
    0.77
    Honestly
    0.77
    ються
    0.76
    Act Density 0.001%

    No Known Activations