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

    Neuronpedia

    INDEX
    Explanations

    check in, Super Premium, Language Models, Standard Deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    objs
    0.24
    ApiService
    0.23
     )
    0.23
    Delimiter
    0.22
    {{
    0.21
     ).
    0.21
    öff
    0.21
                                  
    0.20
    Quantity
    0.20
             
    0.20
    POSITIVE LOGITS
    0.28
     linge
    0.27
    ␣
    0.26
     maid
    0.24
     دی۔
    0.23
     yì
    0.22
    の方
    0.22
    ारा
    0.21
    我们也
    0.21
     ong
    0.21
    Act Density 0.426%

    No Known Activations