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

    Neuronpedia

    INDEX
    Explanations

    ion charges and chemical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    춥
    0.40
     châu
    0.40
     Shelley
    0.39
     Cut
    0.38
    ,(((
    0.38
     Truth
    0.38
     bia
    0.36
    须知
    0.35
     Cuts
    0.35
     vertical
    0.35
    POSITIVE LOGITS
    -,
    1.35
     -,
    1.35
    -;
    1.34
    (-)
    1.28
    -)
    1.27
     '-'
    1.25
    -:
    1.23
    -.
    1.23
     "-"
    1.22
     '-',
    1.22
    Act Density 0.027%

    No Known Activations