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

    Neuronpedia

    INDEX
    Explanations

    Time measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     十
    -0.06
     CCD
    -0.06
     ze
    -0.06
    刀
    -0.06
     qualquer
    -0.06
     prosperity
    -0.06
     Δι
    -0.06
    .disk
    -0.06
     renk
    -0.06
     siege
    -0.06
    POSITIVE LOGITS
    ◆
    0.07
    .contrib
    0.06
    .messages
    0.06
    enchmark
    0.06
     marrow
    0.06
    CellValue
    0.06
     каш
    0.06
    apon
    0.06
     исключ
    0.06
     Among
    0.06
    Act Density 0.026%

    No Known Activations