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

    Neuronpedia

    INDEX
    Explanations

    character names and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是一種
    0.44
    是一家
    0.39
    是一個
    0.39
    follows
    0.39
    striatis
    0.39
     পূর্ববাংলা
    0.38
    𒐪
    0.37
    是一种
    0.37
     loosely
    0.37
     useNewUrlParser
    0.37
    POSITIVE LOGITS
     incessant
    0.46
    、
    0.45
     unbearable
    0.43
     و
    0.42
     sobbing
    0.42
    และ
    0.42
     bouton
    0.41
     fratello
    0.41
     and
    0.40
     emot
    0.40
    Act Density 0.030%

    No Known Activations