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

    Neuronpedia

    INDEX
    Explanations

    NSAID, aspirin, SSD, resume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    1.88
    ي
    1.68
    ان
    1.66
    zelfde
    1.66
    ا
    1.45
    yah
    1.43
    на
    1.37
    ių
    1.34
    い
    1.33
    י
    1.33
    POSITIVE LOGITS
    你
    1.34
    })
    1.20
     등
    1.17
    },
    1.15
    ES
    1.06
    )
    1.06
    做
    1.05
    ),
    1.03
    ון
    1.02
    등
    1.02
    Act Density 0.027%

    No Known Activations