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

    Neuronpedia

    INDEX
    Explanations

    approach, major step, strong head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    1.28
     МВД
    1.05
    в
    1.04
    ummers
    1.02
    理
    1.00
    erv
    1.00
    mph
    1.00
    oda
    1.00
     abbreviated
    0.99
    qh
    0.99
    POSITIVE LOGITS
     discharg
    1.23
     возможности
    1.23
     možno
    1.19
    ্যান
    1.17
     induc
    1.16
    遷
    1.10
     potentiel
    1.09
    𝐠
    1.05
    ژگی
    1.05
    DISABLE
    1.05
    Act Density 0.001%

    No Known Activations