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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :UIControlEvent
    -0.07
    LAS
    -0.06
    !=↵
    -0.06
     "*",
    -0.06
    [of
    -0.06
    _SAMPLE
    -0.06
        ↵    ↵    ↵
    -0.06
    ?>">↵
    -0.06
    865
    -0.06
    Filtered
    -0.06
    POSITIVE LOGITS
     blond
    0.08
     Wired
    0.07
    esse
    0.07
    飛
    0.07
    tains
    0.06
     Lawrence
    0.06
    สามารถ
    0.06
    (metadata
    0.06
    ey
    0.06
     ora
    0.06
    Act Density 0.001%

    No Known Activations