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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     meteen
    0.71
     direto
    0.70
     сразу
    0.68
     damning
    0.66
     whopping
    0.64
    measured
    0.63
     drenched
    0.59
     claimed
    0.59
     напрямую
    0.59
    override
    0.59
    POSITIVE LOGITS
     Occasionally
    0.95
     occasionally
    0.89
     occasional
    0.88
    Occasionally
    0.79
    ുകയും
    0.74
     Certaines
    0.73
     አንዳንድ
    0.73
     Whenever
    0.72
    بعض
    0.71
     periodically
    0.70
    Act Density 0.000%

    No Known Activations