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

    Neuronpedia

    INDEX
    Explanations

    multi-disciplinary and interdisciplinary concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    0.96
    S
    0.89
    𝙩
    0.85
    𝙙
    0.85
     বন্দ
    0.83
    ST
    0.83
    ăţ
    0.82
    ка
    0.82
    𝚍
    0.82
    SA
    0.81
    POSITIVE LOGITS
    ol
    1.17
    ad
    1.08
     multidiscipl
    1.08
    us
    1.00
     discipline
    0.96
     interdiscipl
    0.96
    ין
    0.96
    ciplinary
    0.93
    f
    0.91
     disciplines
    0.90
    Act Density 0.004%

    No Known Activations