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

    Neuronpedia

    INDEX
    Explanations

    code or documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <SpriteRenderer
    -0.07
    tensorflow
    -0.07
    fre
    -0.07
    into
    -0.07
    RouterModule
    -0.07
    Stamped
    -0.06
     meisjes
    -0.06
    Ин
    -0.06
    names
    -0.06
     concentrating
    -0.06
    POSITIVE LOGITS
     bx
    0.07
     Movie
    0.06
     św
    0.06
    凯
    0.06
    parse
    0.06
     )(
    0.06
    213
    0.06
     suffix
    0.06
    貸
    0.06
    ckeditor
    0.06
    Act Density 0.000%

    No Known Activations