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

    Neuronpedia

    INDEX
    Explanations

    warm up, Interested in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     повышен
    0.78
    i
    0.74
     रवाना
    0.73
    ة
    0.73
    driving
    0.72
     staw
    0.71
    ᅱ
    0.70
     человеком
    0.69
     Ц
    0.69
     общественного
    0.68
    POSITIVE LOGITS
     ambit
    0.78
    午前
    0.77
    EDITORIAL
    0.75
     module
    0.72
    acie
    0.71
     metre
    0.71
     modular
    0.70
    做了
    0.69
    edio
    0.69
     metaphysics
    0.69
    Act Density 0.001%

    No Known Activations