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

    Neuronpedia

    INDEX
    Explanations

    column identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нару
    0.75
    Locks
    0.75
    uzie
    0.73
    يء
    0.73
    #![
    0.72
    Lastly
    0.71
    irii
    0.71
    泣
    0.71
    ع
    0.70
    об
    0.70
    POSITIVE LOGITS
     Armada
    0.85
     Bình
    0.84
     Buh
    0.82
     Bạch
    0.82
     Arms
    0.80
    서는
    0.80
     photocurrent
    0.80
     Nội
    0.78
     Escola
    0.77
     Choosing
    0.77
    Act Density 0.001%

    No Known Activations