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

    Neuronpedia

    INDEX
    Explanations

    Ithaca, physical, streaming, Transform, ARI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ₁+
    0.40
     괜찮
    0.39
    庵
    0.38
     نعمل
    0.37
    ieto
    0.37
     Roper
    0.37
     आयुष्मान
    0.37
    さんも
    0.36
     Inequality
    0.36
     او
    0.36
    POSITIVE LOGITS
    Burst
    0.44
    VENTION
    0.42
    ập
    0.41
     korun
    0.41
     되지
    0.39
    이지
    0.38
    Wings
    0.38
    FFE
    0.38
     филосо
    0.38
    মিন
    0.38
    Act Density 0.000%

    No Known Activations