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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |`↵
    -0.07
    Sec
    -0.07
    <input
    -0.07
    认为
    -0.06
    鸟
    -0.06
     diss
    -0.06
    ?>">↵
    -0.06
     نوشته
    -0.06
    [group
    -0.06
    ]]:↵
    -0.06
    POSITIVE LOGITS
     Irma
    0.07
     kut
    0.07
    atural
    0.06
     sve
    0.06
    dating
    0.06
    celand
    0.06
     hurried
    0.06
    ;$
    0.06
     тих
    0.06
     vt
    0.06
    Act Density 0.004%

    No Known Activations