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

    Neuronpedia

    INDEX
    Explanations

    identification or access cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -1.45
     
    -1.23
     in
    -1.17
     الواقع
    -1.03
     —
    -1.02
     \
    -1.02
     -
    -0.98
    ∷
    -0.98
    BS
    -0.98
    \
    -0.97
    POSITIVE LOGITS
     مخصوص
    1.17
    Программа
    1.16
     holders
    1.16
    adomo
    1.16
     identification
    1.14
     Parla
    1.13
    ―――
    1.13
     getID
    1.13
    //{
    1.12
     holder
    1.11
    Act Density 0.041%

    No Known Activations