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

    Neuronpedia

    INDEX
    Explanations

    sentence endings and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उदा
    0.79
     eg
    0.70
    第一個
    0.69
     deleting
    0.68
    less
    0.68
     magic
    0.68
     volunteering
    0.68
     homework
    0.66
     big
    0.65
     equality
    0.65
    POSITIVE LOGITS
    etera
    1.23
    .),
    1.20
    .).
    1.17
    .;
    1.07
    .],
    1.01
    .?
    1.00
    .—
    0.99
    ."),
    0.97
    .');
    0.96
    .].
    0.95
    Act Density 0.114%

    No Known Activations