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

    Neuronpedia

    INDEX
    Explanations

    behavior and anatomy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चांगले
    0.51
     нулю
    0.49
     грошы
    0.47
     fração
    0.46
     прибыль
    0.45
    UNITY
    0.44
    WholeProgram
    0.44
     общем
    0.43
     IUnary
    0.43
     प्रमाणात
    0.42
    POSITIVE LOGITS
     musi
    0.52
     for
    0.48
     Behavior
    0.47
     behavior
    0.47
    Child
    0.47
    ap
    0.45
    *)
    0.45
     Child
    0.45
     Stickers
    0.45
     muk
    0.44
    Act Density 0.002%

    No Known Activations