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

    Neuronpedia

    INDEX
    Explanations

    D words and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㮆
    0.71
    秅
    0.69
    עה
    0.68
     numberWithFloat
    0.68
    苹
    0.68
    ᄎ
    0.67
    ClFN
    0.66
    𐰆
    0.66
     акции
    0.66
    ᕐ
    0.66
    POSITIVE LOGITS
     ಡ
    1.36
    D
    1.36
     D
    1.34
     ഡ
    1.33
     Д
    1.31
     الد
    1.25
     ਡ
    1.24
     Deutsche
    1.23
    Dead
    1.22
     Doctorate
    1.20
    Act Density 0.829%

    No Known Activations