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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sponsors
    -0.08
    .Success
    -0.08
     działania
    -0.07
     bulk
    -0.07
    -Q
    -0.07
    规避
    -0.07
    גר
    -0.07
     masked
    -0.07
    紧凑
    -0.07
    سار
    -0.07
    POSITIVE LOGITS
     regiment
    0.07
     Burger
    0.07
    组织实施
    0.07
    .Web
    0.06
    金刚
    0.06
    bellion
    0.06
    Dem
    0.06
     Horm
    0.06
     getTime
    0.06
    开发区
    0.06
    Act Density 0.019%

    No Known Activations