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

    Neuronpedia

    INDEX
    Explanations

    deep learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Electricity
    0.79
     ELSE
    0.77
    eneuve
    0.75
    честве
    0.74
    神社
    0.72
    Higher
    0.72
     ویکی‌پدیا
    0.72
    ibility
    0.72
    Ele
    0.71
    Op
    0.69
    POSITIVE LOGITS
     dives
    1.11
     dive
    1.11
    dive
    0.98
     conosc
    0.96
     seated
    0.94
    seated
    0.88
     breaths
    0.87
     breath
    0.87
    ened
    0.85
    gående
    0.85
    Act Density 0.145%

    No Known Activations