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

    Neuronpedia

    INDEX
    Explanations

    EB-2 National Interest Waiver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.24
    u
    1.04
    ो
    1.04
    У
    1.04
    ките
    1.02
     sauvage
    1.02
     negar
    1.01
    ್
    1.01
     爱
    1.00
     chil
    0.99
    POSITIVE LOGITS
    امل
    1.01
    प
    1.00
    ulents
    1.00
    mouseleave
    0.99
    ssdk
    0.96
    imdb
    0.96
    amsu
    0.95
    znam
    0.94
    benhav
    0.94
    mDatas
    0.94
    Act Density 0.001%

    No Known Activations