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

    Neuronpedia

    INDEX
    Explanations

    pytest tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GRP
    -0.08
     Bliss
    -0.06
     thải
    -0.06
     Evidence
    -0.06
    すぎ
    -0.06
     Thủ
    -0.06
     hamm
    -0.06
     posto
    -0.06
    ambre
    -0.06
     Hemp
    -0.06
    POSITIVE LOGITS
    -Л
    0.07
    IMIT
    0.06
     Fletcher
    0.06
    ивать
    0.06
     lettuce
    0.06
     Т
    0.06
     suffix
    0.05
    -social
    0.05
    ('.');↵
    0.05
    0.05
    Act Density 0.012%

    No Known Activations