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

    Neuronpedia

    INDEX
    Explanations

    explaining *only* to fulfill request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     because
    0.38
    ،
    0.35
     karena
    0.32
     omdat
    0.31
    because
    0.30
     porque
    0.30
     with
    0.30
     क्योंकि
    0.30
    ,
    0.29
     لأن
    0.29
    POSITIVE LOGITS
     your
    0.25
     velič
    0.22
     আপনার
    0.22
     თქვენ
    0.22
     you
    0.22
    恼
    0.21
     votre
    0.21
    आपके
    0.21
    您
    0.21
    ėtų
    0.21
    Act Density 0.004%

    No Known Activations