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

    Neuronpedia

    INDEX
    Explanations

    to be able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    primarily
    0.84
    സ്വ
    0.82
    ዋ
    0.79
     particularmente
    0.78
     özellikle
    0.77
    0.76
     vooral
    0.76
     soprattutto
    0.76
    ijas
    0.76
    particularly
    0.75
    POSITIVE LOGITS
     able
    1.17
     order
    1.12
     hope
    1.10
     hopes
    1.08
    能够
    1.01
     hoping
    1.00
     come
    0.97
     чтобы
    0.96
     determine
    0.95
     nhằm
    0.89
    Act Density 0.101%

    No Known Activations