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

    Neuronpedia

    INDEX
    Explanations

    hotel manager AI decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کل
    0.46
    Ми
    0.44
    otros
    0.43
    ми
    0.42
    Nome
    0.42
    National
    0.41
    Те
    0.41
     pounded
    0.41
    Fl
    0.41
    サン
    0.41
    POSITIVE LOGITS
     lẻ
    0.43
    venture
    0.39
     merch
    0.38
    诰
    0.38
    lán
    0.38
    getBlock
    0.37
    studentRecord
    0.37
    纪
    0.37
    ứ
    0.36
    ürdig
    0.36
    Act Density 0.001%

    No Known Activations