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

    Neuronpedia

    INDEX
    Explanations

    restrictions and temporary files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.02
    y
    0.96
     in
    0.90
     N
    0.86
    t
    0.86
    ik
    0.86
     on
    0.82
     Bunu
    0.81
    l
    0.81
    k
    0.79
    POSITIVE LOGITS
    цы
    0.95
    ным
    0.85
    меры
    0.85
    лый
    0.79
    ды
    0.79
    られて
    0.79
    торы
    0.78
    decimals
    0.78
    restrictions
    0.78
    ার্স
    0.77
    Act Density 0.015%

    No Known Activations