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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ASCII
    0.53
     지속
    0.52
     taxon
    0.52
     grep
    0.51
     COMMIT
    0.49
     가장
    0.49
    㚘
    0.49
     BEGIN
    0.48
     IPv
    0.47
    檄
    0.47
    POSITIVE LOGITS
    cut
    0.46
    four
    0.46
    Cut
    0.45
    How
    0.45
    Both
    0.44
    In
    0.44
    cho
    0.44
    Next
    0.44
    Vis
    0.43
    Let
    0.42
    Act Density 0.129%

    No Known Activations