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

    Neuronpedia

    INDEX
    Explanations

    capital cities of countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    と共に
    0.38
    从而
    0.36
    さんと
    0.36
     거고
    0.36
     туда
    0.35
    所で
    0.35
     그래서
    0.34
     بتوان
    0.34
     যাদের
    0.33
    别人的
    0.33
    POSITIVE LOGITS
     consists
    0.82
     είναι
    0.76
     is
    0.76
     are
    0.71
     differs
    0.67
     jsou
    0.60
     involves
    0.59
     comprises
    0.59
     bestaat
    0.57
     transcends
    0.57
    Act Density 0.090%

    No Known Activations