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

    Neuronpedia

    INDEX
    Explanations

    flat Earth model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ма
    1.18
    І
    1.09
     पुरुष
    1.07
    മൂഹ
    1.03
    nya
    1.00
    center
    0.99
    త్వం
    0.97
    ೂರ್ಯ
    0.95
    дуу
    0.95
    ially
    0.94
    POSITIVE LOGITS
    ar
    1.28
    el
    1.24
     kinase
    1.09
    ﺴ
    1.08
    骜
    1.08
     afterDir
    1.08
    en
    1.08
    arono
    1.06
    াবির
    1.05
     enterprise
    1.05
    Act Density 0.002%

    No Known Activations