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

    Neuronpedia

    INDEX
    Explanations

    teaspoon, pneumonia, plantarum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ya
    1.04
    es
    1.00
    tion
    0.98
     Ya
    0.94
    Help
    0.85
    Dynamic
    0.85
    ড্ড
    0.82
    Extreme
    0.80
    DNA
    0.80
    Helper
    0.80
    POSITIVE LOGITS
     agréable
    1.44
     فيها
    1.37
    倞
    1.34
    cké
    1.24
    ോട്ടോ
    1.22
     إليها
    1.20
     LPTMR
    1.20
     agradable
    1.20
    ována
    1.17
    িয়ায়
    1.16
    Act Density 0.002%

    No Known Activations