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

    Neuronpedia

    INDEX
    Explanations

    running application with debug or host

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.54
    )
    0.52
     it
    0.50
    >
    0.49
    ↵
    0.49
    }
    0.47
     age
    0.45
     twisting
    0.44
    ]
    0.43
    u
    0.43
    POSITIVE LOGITS
    boBox
    0.46
    evším
    0.46
     Pogis
    0.46
    న్‌లో
    0.45
     Lobkovic
    0.45
    личие
    0.44
     attham
    0.44
     permitem
    0.44
     méthodique
    0.42
     fudai
    0.42
    Act Density 0.001%

    No Known Activations