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

    Neuronpedia

    INDEX
    Explanations

    thumbnail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cast
    -0.09
     Actor
    -0.08
     Scott
    -0.07
     Cort
    -0.07
    coc
    -0.07
     Act
    -0.07
    Pag
    -0.07
     akce
    -0.07
    ồi
    -0.07
     degrees
    -0.07
    POSITIVE LOGITS
    thumbnail
    0.10
     thumb
    0.09
    thumb
    0.09
    _thumbnail
    0.08
     thumbnail
    0.07
    .thumbnail
    0.07
     Chew
    0.07
    Thumbnail
    0.07
     inadequate
    0.07
    <u
    0.07
    Act Density 0.002%

    No Known Activations