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

    Neuronpedia

    INDEX
    Explanations

    ancient writers and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innovación
    0.46
     innovate
    0.45
     uncompromising
    0.44
     முழுக்க
    0.44
    规定
    0.44
     précise
    0.43
     проведение
    0.42
     activism
    0.42
     innovator
    0.42
    羮
    0.42
    POSITIVE LOGITS
    writers
    0.41
     curiously
    0.41
     escritores
    0.41
     themselves
    0.40
     writers
    0.40
     postcards
    0.39
    various
    0.38
     관심을
    0.38
    igrams
    0.37
     poets
    0.37
    Act Density 0.022%

    No Known Activations