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

    Neuronpedia

    INDEX
    Explanations

    eyes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    excerpt
    -0.07
    patterns
    -0.06
    Tiles
    -0.06
    Editors
    -0.06
    <Link
    -0.06
     Bedroom
    -0.06
    .fake
    -0.06
    ^-
    -0.06
    translation
    -0.06
     cabinet
    -0.06
    POSITIVE LOGITS
     corre
    0.07
     opted
    0.07
     صاحب
    0.06
     widened
    0.06
     Bearings
    0.06
     ヽ
    0.06
    dex
    0.06
     κοι
    0.06
     left
    0.06
     pseudo
    0.06
    Act Density 0.009%

    No Known Activations