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

    Neuronpedia

    INDEX
    Explanations

    missing data and keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    収納
    1.16
    一覧
    1.07
    urance
    1.06
    해도
    1.05
    ствий
    1.04
    asku
    1.03
    asters
    1.02
    localization
    1.00
    urrences
    1.00
    adoff
    1.00
    POSITIVE LOGITS
     and
    2.01
     và
    1.88
     और
    1.87
     आणि
    1.83
     ול
    1.74
     Và
    1.74
     και
    1.74
     ו
    1.72
     ומ
    1.71
    และ
    1.68
    Act Density 0.000%

    No Known Activations