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

    Neuronpedia

    INDEX
    Explanations

    documentation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     XP
    0.86
     Save
    0.86
     Stomach
    0.85
     Retry
    0.82
     Submit
    0.81
     Saver
    0.79
     rechercher
    0.78
     Unlock
    0.76
     Undo
    0.75
     subscriber
    0.75
    POSITIVE LOGITS
    Fuente
    0.76
    Document
    0.75
    Wh
    0.74
    Sound
    0.70
    这篇文章
    0.69
    Weeks
    0.68
    describe
    0.67
    True
    0.67
    Alla
    0.67
    sound
    0.67
    Act Density 0.000%

    No Known Activations