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

    Neuronpedia

    INDEX
    Explanations

    expressing sentiment or opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atau
    0.82
     obeys
    0.79
    ?
    0.76
     benar
    0.75
     berapa
    0.75
     truly
    0.74
     fulfills
    0.73
     dan
    0.72
     telah
    0.71
     fulfilled
    0.71
    POSITIVE LOGITS
    担忧
    0.85
    клика
    0.80
    看法
    0.77
    自身の
    0.76
    sentiment
    0.74
    谴
    0.72
     blaming
    0.71
    emotional
    0.68
    بد
    0.68
     эмоциона
    0.68
    Act Density 0.148%

    No Known Activations