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

    Neuronpedia

    INDEX
    Explanations

    Consider me your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undisclosed
    0.46
     restaurants
    0.46
     foodservice
    0.46
     facilitates
    0.44
     loans
    0.44
     insures
    0.44
     phosphates
    0.43
     services
    0.43
     eatery
    0.43
     listings
    0.43
    POSITIVE LOGITS
     в
    0.51
    ро
    0.51
     psicol
    0.49
     nuovi
    0.48
     새로운
    0.48
     menacing
    0.46
    新たな
    0.46
    瞠
    0.46
     nuova
    0.45
    人工智能
    0.45
    Act Density 0.005%

    No Known Activations