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

    Neuronpedia

    INDEX
    Explanations

    MyComponentStyled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ADOW
    0.85
    0.78
    রাষ্ট্র
    0.77
     ESC
    0.77
     Pizza
    0.76
    Scar
    0.76
     Scar
    0.75
     Norwood
    0.75
     sab
    0.74
     Libert
    0.73
    POSITIVE LOGITS
     Along
    0.73
    Along
    0.73
     Keeping
    0.71
    Keeping
    0.71
    Meine
    0.68
     گم
    0.68
     Jennings
    0.67
     Meine
    0.67
    Keep
    0.66
     मझ
    0.66
    Act Density 0.357%

    No Known Activations