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

    Neuronpedia

    INDEX
    Explanations

    definitions after where:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ചിത്രം
    0.47
    '`--
    0.46
     `'\\
    0.44
    écution
    0.41
    𒁾
    0.40
     guérison
    0.40
     ограничењима
    0.40
    <unused76>
    0.39
    тинг
    0.39
     processus
    0.39
    POSITIVE LOGITS
     variables
    0.76
    variables
    0.66
    where
    0.65
     Variables
    0.62
     symbols
    0.61
    Variables
    0.61
     where
    0.53
    vars
    0.53
     parameters
    0.52
    Where
    0.52
    Act Density 0.003%

    No Known Activations