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

    Neuronpedia

    INDEX
    Explanations

    personal beliefs and thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     упомина
    1.01
     erwähnt
    1.00
     Mention
    0.97
     mentioning
    0.96
     mentioned
    0.95
     mention
    0.94
    Mention
    0.90
    备注
    0.90
    提及
    0.87
     mencionó
    0.87
    POSITIVE LOGITS
     believe
    1.63
     believes
    1.60
    我认为
    1.51
    認為
    1.46
    认为
    1.46
     belief
    1.45
    believe
    1.37
     argue
    1.34
     argument
    1.30
     argues
    1.29
    Act Density 0.144%

    No Known Activations