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

    Neuronpedia

    INDEX
    Explanations

    distance calculation or measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يل
    0.97
    ’
    0.84
    ح
    0.71
    )
    0.68
    ه‌
    0.68
    ))
    0.65
     einzigen
    0.65
    )}
    0.64
    la
    0.64
    き
    0.64
    POSITIVE LOGITS
    is
    1.19
     distance
    1.14
    ing
    1.10
    т
    1.06
     Distance
    1.05
    ת
    1.02
    ت
    0.95
     jarak
    0.94
    a
    0.93
    Distance
    0.89
    Act Density 0.015%

    No Known Activations