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

    Neuronpedia

    INDEX
    Explanations

    things get or are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoặc
    0.67
    বর্তী
    0.66
    を除く
    0.66
     ​​
    0.61
    ors
    0.59
    を有する
    0.59
    ạ
    0.59
    ants
    0.58
    ischen
    0.58
    ager
    0.57
    POSITIVE LOGITS
    ي
    0.80
    يًا
    0.79
    tions
    0.78
    aient
    0.77
    DetailUI
    0.76
     böyle
    0.75
    لے
    0.73
    mDatas
    0.73
    żliw
    0.71
    りは
    0.70
    Act Density 0.004%

    No Known Activations