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

    Neuronpedia

    INDEX
    Explanations

    GitHub Copilot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ния
    0.75
    ls
    0.62
    я
    0.60
    ;
    0.60
    ى
    0.59
    ร
    0.58
     робо
    0.57
    ح
    0.57
    ros
    0.55
    ü
    0.55
    POSITIVE LOGITS
     don
    0.74
     and
    0.71
    LSTM
    0.70
     OPEC
    0.68
    وک
    0.67
    Menu
    0.66
    の色
    0.65
     pekan
    0.65
    Length
    0.64
    Qatar
    0.64
    Act Density 0.000%

    No Known Activations