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

    Neuronpedia

    INDEX
    Explanations

    legal proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .population
    -0.08
    .za
    -0.07
    (selection
    -0.07
    グラ
    -0.07
     Prize
    -0.06
    ?";↵
    -0.06
     dicho
    -0.06
    :",↵
    -0.06
     Approx
    -0.06
     indication
    -0.06
    POSITIVE LOGITS
     arab
    0.06
    ало
    0.06
    Brad
    0.06
    atég
    0.06
    ALLE
    0.06
    を見
    0.06
     schem
    0.06
    ‌پدیای
    0.06
     avatar
    0.06
    .path
    0.06
    Act Density 0.006%

    No Known Activations