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

    Neuronpedia

    INDEX
    Explanations

    sentence structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मियल
    1.10
    ೂರ್ವ
    1.09
    ເພື່ອ
    1.02
    하였
    1.00
    ophora
    0.98
    liono
    0.96
    원본파일명
    0.96
    োষণ
    0.95
     समाजसेवी
    0.95
    하였다
    0.95
    POSITIVE LOGITS
    s
    1.73
     the
    1.24
    t
    1.16
     this
    1.13
    ↵
    1.05
    ,
    1.02
     data
    0.96
    ों
    0.95
     stunning
    0.93
    sü
    0.86
    Act Density 0.003%

    No Known Activations