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

    Neuronpedia

    INDEX
    Explanations

    returns the index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    li
    0.51
    闥
    0.48
    itt
    0.47
    ities
    0.47
    人材
    0.46
    nd
    0.45
    glichkeiten
    0.45
    ית
    0.44
    l
    0.44
    е
    0.44
    POSITIVE LOGITS
     poprzed
    0.46
     unw
    0.45
     tink
    0.43
     रिव
    0.42
    റിയ
    0.41
     vorige
    0.41
     excitedly
    0.40
    ሳይ
    0.40
     electricians
    0.40
     ungew
    0.40
    Act Density 0.002%

    No Known Activations