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

    Neuronpedia

    INDEX
    Explanations

    code block endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दोन
    0.40
    मध्ये
    0.38
     असून
    0.37
     தாவர
    0.37
    विषयी
    0.37
     केवळ
    0.36
    }--\
    0.36
     त्याच्या
    0.36
    തോ
    0.35
    $-[
    0.35
    POSITIVE LOGITS
    ↵
    0.52
    ↵↵
    0.48
    ↵↵↵
    0.38
     Thus
    0.37
     update
    0.37
     Additionally
    0.36
     For
    0.35
     All
    0.35
     गौरतलब
    0.34
    <0x0D>
    0.34
    Act Density 0.071%

    No Known Activations