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

    Neuronpedia

    INDEX
    Explanations

    systems and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zię
    0.51
     đầu
    0.49
    ின
    0.48
    ᄆ
    0.48
     അവരുടെ
    0.47
     करेंगी
    0.45
    łę
    0.45
     ধৈর্য
    0.44
    Wh
    0.44
     instruções
    0.44
    POSITIVE LOGITS
     Drug
    0.48
     Cyber
    0.43
    semb
    0.43
     Prep
    0.43
     Radar
    0.43
     Git
    0.42
     Coal
    0.42
     Allahabad
    0.42
     Life
    0.42
     Karma
    0.42
    Act Density 0.002%

    No Known Activations