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

    Neuronpedia

    INDEX
    Explanations

    specific patterns related to numerical or mathematical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Symbols or abbreviations with hyphens/dashes

    np_acts-logits-general · gemini-2.0-flash

    symbols and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.95
    +#+#
    -0.74
    ########.
    -0.72
    Personensuche
    -0.67
    fromnode
    -0.67
    Autoritní
    -0.67
     Roskov
    -0.66
    UnusedPrivate
    -0.60
     Италијани
    -0.60
    setVerticalGroup
    -0.60
    POSITIVE LOGITS
    󠁢
    0.80
     MainAxisSize
    0.77
     varandra
    0.63
     InputDecoration
    0.59
     Theſe
    0.57
     chré
    0.57
    lillah
    0.56
     wavy
    0.56
    󠁮
    0.54
    stretchr
    0.54
    Act Density 0.342%

    No Known Activations