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

    Neuronpedia

    INDEX
    Explanations

    python language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.76
     "
    0.72
     lagu
    0.68
     The
    0.65
     We
    0.64
      
    0.63
    ↵
    0.61
     I
    0.60
     All
    0.58
     `
    0.58
    POSITIVE LOGITS
     或者
    1.04
     或
    1.03
     hoặc
    0.99
     ಅಥವಾ
    0.89
    abhut
    0.88
    퐫
    0.85
     または
    0.85
    étaire
    0.85
    ெற்ற
    0.84
     alebo
    0.84
    Act Density 0.099%

    No Known Activations