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

    Neuronpedia

    INDEX
    Explanations

    javascript `.catch` error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ബ്ര
    0.44
    📓
    0.42
     sages
    0.41
     dredging
    0.40
     Exceptions
    0.39
    র্প
    0.38
    BERS
    0.38
    冫
    0.38
     resizing
    0.38
    British
    0.37
    POSITIVE LOGITS
    당
    0.39
    assert
    0.39
    为
    0.38
     스트
    0.38
    ジェ
    0.38
    post
    0.38
     incluso
    0.38
    generator
    0.37
     Incluso
    0.37
     post
    0.35
    Act Density 0.002%

    No Known Activations