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

    Neuronpedia

    INDEX
    Explanations

    Special Relativity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ிஸ்த
    0.95
    ીર
    0.91
    მწიფ
    0.88
     pries
    0.86
    ीकरण
    0.84
     mascar
    0.80
    ่
    0.80
    нили
    0.79
    க்கொண்ட
    0.78
     pilgr
    0.77
    POSITIVE LOGITS
    th
    1.13
    ot
    1.05
    di
    0.98
    "
    0.96
    ді
    0.95
    al
    0.95
    ج
    0.92
    ೨
    0.91
    egen
    0.89
    de
    0.88
    Act Density 0.002%

    No Known Activations