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

    Neuronpedia

    INDEX
    Explanations

    reconstruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mark
    -0.07
     hs
    -0.07
     markdown
    -0.06
    Karen
    -0.06
    URL
    -0.06
    Award
    -0.06
    enguins
    -0.06
     Woods
    -0.06
     mineral
    -0.06
    とっても
    -0.06
    POSITIVE LOGITS
    (',',
    0.08
     onFinish
    0.07
     PyErr
    0.07
     Exclusive
    0.07
    停留
    0.07
    צועי
    0.07
     hiatus
    0.07
    '";↵
    0.07
    _lineno
    0.07
    篑
    0.06
    Act Density 0.004%

    No Known Activations