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

    Neuronpedia

    INDEX
    Explanations

    speed, class, and pursuit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.43
    atam
    0.43
    id
    0.43
     solenoid
    0.39
    amis
    0.38
    idin
    0.38
     प्रा
    0.38
    advertise
    0.38
    屏
    0.37
    סף
    0.37
    POSITIVE LOGITS
     दिलाया
    0.52
     கருத்து
    0.47
     тенден
    0.47
     Бүгенге
    0.46
    夭
    0.46
    thorace
    0.46
     договору
    0.46
    苳
    0.46
     plummeted
    0.45
    ]'
    0.45
    Act Density 0.000%

    No Known Activations