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

    Neuronpedia

    INDEX
    Explanations

    obtain what you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     छत्तीसगढ़
    0.93
     staf
    0.91
     Provo
    0.88
     SoC
    0.86
     EMF
    0.86
     ALU
    0.86
    y
    0.86
     bash
    0.86
    ี
    0.86
     данни
    0.84
    POSITIVE LOGITS
    اسة
    0.91
    ແລະ
    0.88
    ان
    0.85
    ཿ
    0.83
    และความ
    0.81
    increased
    0.80
    ستہ
    0.80
    ᄈ
    0.79
    ❤❤
    0.79
    នៃ
    0.77
    Act Density 0.054%

    No Known Activations