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

    Neuronpedia

    INDEX
    Explanations

    only thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    但不
    0.42
     помо
    0.41
     Already
    0.40
     Somewhere
    0.38
    很大
    0.38
    very
    0.37
    장을
    0.36
    another
    0.36
    emorrh
    0.36
    kipun
    0.35
    POSITIVE LOGITS
     truly
    0.78
     wirklich
    0.74
     veramente
    0.74
     eneste
    0.74
     remaining
    0.72
     einzigen
    0.71
     übrig
    0.70
     einzige
    0.70
     reliably
    0.68
    唯一的
    0.68
    Act Density 0.019%

    No Known Activations