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

    Neuronpedia

    INDEX
    Explanations

    list items or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otot
    0.37
     عنا
    0.35
     Pred
    0.35
     Streaming
    0.35
     nisso
    0.35
     پیش
    0.35
     lavoro
    0.35
     سین
    0.34
    oxifen
    0.33
    之时
    0.33
    POSITIVE LOGITS
    except
    0.38
    Except
    0.35
     whether
    0.35
     including
    0.34
     except
    0.34
     youll
    0.34
    you
    0.34
    un
    0.33
    e
    0.33
     most
    0.33
    Act Density 0.000%

    No Known Activations