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

    Neuronpedia

    INDEX
    Explanations

    whole grains, official Academy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cóm
    0.40
    )+\
    0.40
    immen
    0.38
     zumindest
    0.37
     significative
    0.37
    にも
    0.37
    therapeutic
    0.37
    寅
    0.36
    erto
    0.36
     dorado
    0.36
    POSITIVE LOGITS
    抜
    0.44
    Bibitem
    0.42
     ISZ
    0.41
    考試
    0.41
    萑
    0.40
     Fools
    0.40
     袋
    0.39
     McClure
    0.38
    噘
    0.38
     `'
    0.38
    Act Density 0.000%

    No Known Activations