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

    Neuronpedia

    INDEX
    Explanations

    Formatting for options or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (‘
    0.43
     ('
    0.36
    ('-',
    0.35
     tricks
    0.33
     («
    0.33
     月
    0.31
    ities
    0.30
    ('/',
    0.30
    ⟋
    0.30
     etc
    0.29
    POSITIVE LOGITS
     "...
    0.75
     "[
    0.68
    "...
    0.68
    "[
    0.64
     “…
    0.63
    "(
    0.61
     "\(
    0.61
     "..
    0.60
     "(
    0.60
     "'
    0.57
    Act Density 0.215%

    No Known Activations