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

    Neuronpedia

    INDEX
    Explanations

    .api

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IO
    -0.07
    ��
    -0.06
     comprised
    -0.06
     dinner
    -0.06
    oir
    -0.06
     fu
    -0.06
    TRANSFER
    -0.06
     tranqu
    -0.06
    jekt
    -0.06
     ^(
    -0.06
    POSITIVE LOGITS
    ,row
    0.06
    又
    0.06
     Anthrop
    0.06
    .ad
    0.06
     مسلمان
    0.06
     bütün
    0.06
    andard
    0.06
    feature
    0.06
     Of
    0.06
     제가
    0.06
    Act Density 0.002%

    No Known Activations