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

    Neuronpedia

    INDEX
    Explanations

    Shawshank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    去世
    0.55
     प्रकल्
    0.49
     הוא
    0.48
     possibilidades
    0.47
     লড়াই
    0.47
    合せ
    0.47
     परियोजना
    0.45
    ␶
    0.45
     цели
    0.45
    畯
    0.45
    POSITIVE LOGITS
     Smart
    0.47
    lucky
    0.40
    because
    0.40
     newbie
    0.39
     Been
    0.39
     earned
    0.39
    പ്പിച്ച
    0.39
    compl
    0.39
     Archim
    0.38
    Smart
    0.38
    Act Density 0.014%

    No Known Activations