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

    Neuronpedia

    INDEX
    Explanations

    important notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Find
    0.68
    それぞれ
    0.65
    Create
    0.63
    E
    0.63
     curriculum
    0.59
     Create
    0.58
     Locate
    0.57
    Tab
    0.56
    既に
    0.56
     Find
    0.55
    POSITIVE LOGITS
     importanti
    0.87
     важное
    0.86
     penting
    0.83
     важ
    0.81
     важно
    0.79
     важных
    0.79
    很重要
    0.79
    important
    0.77
     important
    0.75
     importante
    0.74
    Act Density 0.000%

    No Known Activations