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

    Neuronpedia

    INDEX
    Explanations

    making you think of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    譎
    0.70
     penjelasan
    0.70
     কার্যক্রম
    0.69
     claiming
    0.68
     સંપ
    0.67
     poter
    0.67
    rać
    0.67
     partecipare
    0.67
     документи
    0.67
     ufficial
    0.65
    POSITIVE LOGITS
     thoughts
    2.21
    想到
    2.04
     thinking
    2.04
     thought
    2.02
     Thoughts
    2.01
     Thinking
    1.96
    Thinking
    1.96
    Think
    1.93
     think
    1.91
    Thoughts
    1.90
    Act Density 0.450%

    No Known Activations