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

    Neuronpedia

    INDEX
    Explanations

    Date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    861
    -0.07
    nama
    -0.07
     Guatemala
    -0.07
     conte
    -0.06
    tractor
    -0.06
     jednot
    -0.06
    Mutex
    -0.06
    นก
    -0.06
     undis
    -0.06
     internals
    -0.06
    POSITIVE LOGITS
    <IActionResult
    0.07
     rack
    0.06
    -au
    0.06
     chảy
    0.06
    <_
    0.06
     deliberately
    0.06
    .grad
    0.06
     seperate
    0.06
    rst
    0.06
    ----↵
    0.06
    Act Density 0.002%

    No Known Activations