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

    Neuronpedia

    INDEX
    Explanations

    reliance or dependency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मं
    0.36
    rasse
    0.36
     Daunting
    0.35
     merhabalar
    0.35
     Swann
    0.35
    atern
    0.33
     kaug
    0.33
    odenal
    0.33
    足以
    0.33
     पहनने
    0.33
    POSITIVE LOGITS
     rely
    2.70
     relies
    2.56
     relying
    2.41
     reliant
    2.39
     reliance
    2.34
    依赖
    2.23
     relied
    2.22
     Rely
    2.20
     depend
    2.06
    依靠
    2.02
    Act Density 0.067%

    No Known Activations