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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foreseeable
    -0.07
     excerpt
    -0.07
    ワー
    -0.06
     Detroit
    -0.06
    .section
    -0.06
    (sf
    -0.06
    Scanner
    -0.06
     Euros
    -0.06
    正常
    -0.06
    ervlet
    -0.06
    POSITIVE LOGITS
     आय
    0.07
     Auth
    0.06
    AGING
    0.06
    ][(
    0.06
     mr
    0.06
     scaff
    0.06
    лены
    0.06
     S
    0.06
    (tex
    0.06
    riend
    0.06
    Act Density 0.017%

    No Known Activations