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

    Neuronpedia

    INDEX
    Explanations

    things that offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    becomes
    0.51
     deviennent
    0.46
     entsteht
    0.43
     Finds
    0.40
     बाव
    0.40
     zostać
    0.40
     devient
    0.39
     tìm
    0.39
     Gotta
    0.38
     encontra
    0.38
    POSITIVE LOGITS
     tilby
    1.11
     offer
    1.10
     erbjuder
    1.10
     offers
    1.09
     menawarkan
    1.05
     nabíz
    0.98
     oferece
    0.95
     ofrecen
    0.95
     offering
    0.94
     offrent
    0.94
    Act Density 0.038%

    No Known Activations