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

    Neuronpedia

    INDEX
    Explanations

    in the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ControlEvents
    0.68
    개
    0.68
    개를
    0.68
     quieras
    0.65
    場合
    0.63
    개의
    0.62
     unico
    0.62
    ंग
    0.62
    getItems
    0.61
     سبق
    0.61
    POSITIVE LOGITS
    ویں
    0.83
    üedad
    0.80
    queda
    0.77
    ুর
    0.76
     confounding
    0.73
    am
    0.72
    inė
    0.72
    ķ
    0.69
    urgiu
    0.69
    ન
    0.68
    Act Density 0.080%

    No Known Activations