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

    Neuronpedia

    INDEX
    Explanations

    SvelteKit code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tibetan
    0.60
     Tibet
    0.55
     Himalayan
    0.49
     Nepal
    0.49
     Himachal
    0.47
     Mongolia
    0.46
    Nepal
    0.46
     primitive
    0.45
     Xinjiang
    0.45
     Tian
    0.44
    POSITIVE LOGITS
    쯜
    0.50
     SISO
    0.47
    UIC
    0.41
    matric
    0.41
    ௭
    0.41
     strtotime
    0.41
    LayoutPanel
    0.40
    ፫
    0.40
     क्रिसमस
    0.40
    窈
    0.40
    Act Density 0.003%

    No Known Activations