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

    Neuronpedia

    INDEX
    Explanations

    positional words followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     langfrist
    0.39
     learnings
    0.39
     salaried
    0.37
     profitability
    0.36
     affordability
    0.36
     nonprofit
    0.34
     pursuant
    0.34
     unprofessional
    0.34
     employability
    0.34
     chatbots
    0.34
    POSITIVE LOGITS
     glistening
    0.43
     billowing
    0.40
     outstretched
    0.37
     gently
    0.36
    旋转
    0.36
     shimmering
    0.35
    墙
    0.35
     drooping
    0.34
     возле
    0.34
     gleaming
    0.33
    Act Density 2.906%

    No Known Activations