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

    Neuronpedia

    INDEX
    Explanations

    Constitutional AI, suggestions, lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEE
    0.52
     Taipei
    0.52
    叼
    0.52
    ال
    0.52
    نا
    0.52
     Open
    0.52
     Enabling
    0.52
    ח
    0.50
    Open
    0.49
     Oahu
    0.49
    POSITIVE LOGITS
    :
    0.66
    ),
    0.53
     disputes
    0.53
    ién
    0.52
    *
    0.52
     inex
    0.51
     poitrine
    0.51
     incessant
    0.51
    3
    0.51
    ۔
    0.51
    Act Density 0.000%

    No Known Activations