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

    Neuronpedia

    INDEX
    Explanations

    random module in code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused40>
    0.54
    URNIZOR
    0.47
    न्नाथ
    0.43
    蠵
    0.43
     सुनेंरोक
    0.42
    पीरियंस
    0.42
    माइंडर
    0.41
     جوړونک
    0.41
     বিশ্বাসের
    0.41
    thebetter
    0.41
    POSITIVE LOGITS
    ,
    0.59
    ↵↵
    0.57
    ↵↵↵
    0.52
    ;
    0.50
    ↵
    0.50
    .
    0.49
    -
    0.44
     and
    0.44
     |
    0.42
     #
    0.42
    Act Density 0.029%

    No Known Activations