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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $.
    0.97
     کیا۔
    0.95
    €.
    0.95
     ہوں۔
    0.93
    *.
    0.90
    “.
    0.90
    $.\
    0.89
     (
    0.88
     “.
    0.88
    \".
    0.88
    POSITIVE LOGITS
     Esports
    0.92
     Kaspersky
    0.87
     Luffy
    0.87
     aswell
    0.79
     Realme
    0.79
     smartwatch
    0.78
    खोरी
    0.76
     scammers
    0.76
     PUBG
    0.76
     Accenture
    0.76
    Act Density 0.003%

    No Known Activations