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

    Neuronpedia

    INDEX
    Explanations

    etc. and listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     translocation
    0.23
    此处
    0.22
     formalism
    0.21
    াঃ
    0.21
     ẞ
    0.20
    :[/
    0.20
     wikip
    0.20
    鍒
    0.20
     expression
    0.20
     tagReport
    0.20
    POSITIVE LOGITS
    ↵
    0.41
    ↵↵
    0.30
     etc
    0.29
     Etc
    0.26
     등의
    0.26
    、
    0.26
     тощо
    0.25
    ili
    0.25
     Just
    0.25
     इत्यादि
    0.25
    Act Density 0.909%

    No Known Activations