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

    Neuronpedia

    INDEX
    Explanations

    for financial or contemporary romance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cción
    0.51
    สู
    0.50
    사랑
    0.50
     believes
    0.49
     стрелецкой
    0.48
    பார
    0.47
    IQR
    0.47
     doesn
    0.46
     Maduro
    0.46
    𒉣
    0.45
    POSITIVE LOGITS
    仍
    0.43
     ascending
    0.43
    money
    0.42
    "।
    0.40
    转发
    0.39
    Ｊ
    0.39
    chett
    0.39
     γν
    0.38
     favourable
    0.38
    転
    0.38
    Act Density 0.003%

    No Known Activations