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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ों,
    -0.06
    .HandlerFunc
    -0.06
    Longitude
    -0.06
     excl
    -0.06
    Fed
    -0.06
    촌
    -0.06
    Wrap
    -0.06
     předmět
    -0.06
    ASTE
    -0.06
    "path
    -0.06
    POSITIVE LOGITS
    (bottom
    0.06
     Recomm
    0.06
     giorn
    0.06
    ultiple
    0.06
    др
    0.06
    ('~
    0.06
     alors
    0.06
     hran
    0.06
     bottom
    0.06
     попада
    0.06
    Act Density 0.081%

    No Known Activations