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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unload
    -0.07
    .nasa
    -0.06
    Period
    -0.06
    PRESENT
    -0.06
     Offices
    -0.06
    華
    -0.06
     named
    -0.06
    hay
    -0.06
     maxlen
    -0.06
    ception
    -0.06
    POSITIVE LOGITS
    Look
    0.07
    Comic
    0.06
     bài
    0.06
    ську
    0.06
    -ม
    0.06
    >";↵
    0.06
     bánh
    0.06
    .")
↵
    0.06
     windy
    0.06
    oko
    0.06
    Act Density 0.013%

    No Known Activations