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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    成了
    -0.07
    .Stderr
    -0.07
    !’
    -0.07
     Blur
    -0.06
     bodies
    -0.06
     packages
    -0.06
    they
    -0.06
     Figure
    -0.06
    Their
    -0.06
    タイトル
    -0.06
    POSITIVE LOGITS
     compar
    0.08
     computations
    0.07
     soát
    0.07
     reb
    0.07
    -ref
    0.07
     ERROR
    0.07
    HAV
    0.07
     unfavorable
    0.07
     красот
    0.07
    merge
    0.07
    Act Density 0.016%

    No Known Activations