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

    Neuronpedia

    INDEX
    Explanations

    city, late, situated, digest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AK
    0.52
    Bonjour
    0.52
    Hi
    0.49
    Or
    0.49
    ্বার
    0.48
    Covid
    0.46
    Municipio
    0.44
    Area
    0.44
    Venus
    0.43
    obtenir
    0.43
    POSITIVE LOGITS
    ]=[
    0.45
     Tolerance
    0.45
     trình
    0.44
     मध्ये
    0.44
     दावे
    0.43
    ]}(
    0.43
    သည်
    0.42
    namefont
    0.42
     lợi
    0.42
     Sew
    0.41
    Act Density 0.000%

    No Known Activations