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

    Neuronpedia

    INDEX
    Explanations

    speaking verbs and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     +
    0.79
     !=
    0.77
     =
    0.75
    /
    0.74
    完整的
    0.74
     ==
    0.73
     &
    0.71
     ഉള്ള
    0.70
    (+
    0.69
    اً
    0.68
    POSITIVE LOGITS
     jeudi
    0.99
     menjelaskan
    0.98
    itió
    0.96
     bluntly
    0.95
    <unused2184>
    0.90
    <unused589>
    0.89
     الخميس
    0.89
     말했다
    0.89
     Pourquoi
    0.88
     지난해
    0.88
    Act Density 0.074%

    No Known Activations