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

    Neuronpedia

    INDEX
    Explanations

    words ending in ated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    馓
    -2.73
    ING
    -2.58
    give
    -2.50
    -2.50
    could
    -2.44
    都是
    -2.39
    -2.36
    และ
    -2.30
     mangiare
    -2.30
     analisi
    -2.27
    POSITIVE LOGITS
    ated
    3.03
    ,”
    2.73
    ating
    2.69
     zumindest
    2.53
     multifaceted
    2.48
     “[
    2.41
    ↵
    2.38
    -”
    2.17
    鬟
    2.14
     â
    2.13
    Act Density 0.051%

    No Known Activations