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

    Neuronpedia

    INDEX
    Explanations

    properties, types, demographics, anonymous, adapt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     movie
    0.44
     ò
    0.40
     mir
    0.39
     cinq
    0.39
     Compose
    0.39
     contoured
    0.39
     രൂപ
    0.38
     discover
    0.38
     AV
    0.38
     dawn
    0.38
    POSITIVE LOGITS
    Warum
    0.44
    ֻ
    0.40
    苧
    0.40
     adiabatically
    0.39
    ിച്ചത്
    0.39
     Entscheid
    0.39
    這樣子
    0.39
    眇
    0.38
    adec
    0.38
     Alters
    0.38
    Act Density 0.000%

    No Known Activations