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

    Neuronpedia

    INDEX
    Explanations

    LaTeX image and formatting commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ኘት
    1.27
     Asalamualaikum
    1.27
    Typography
    1.24
    Giá
    1.17
     ReturnVal
    1.17
    rī
    1.17
    ഘടന
    1.16
     నేపథ
    1.16
    Caption
    1.15
    goài
    1.14
    POSITIVE LOGITS
    ↵↵
    1.14
     all
    1.14
     more
    1.06
     like
    1.04
    s
    1.01
    ,
    0.97
     from
    0.96
    0.96
    .
    0.95
     one
    0.94
    Act Density 0.001%

    No Known Activations