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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -\
    0.40
    Moment
    0.38
    No
    0.37
    That
    0.37
     घट
    0.36
    undefined
    0.35
     Moment
    0.35
    renowned
    0.35
     refers
    0.35
    diabetes
    0.35
    POSITIVE LOGITS
    겠지만
    0.56
    但是在
    0.46
     lakini
    0.46
     nhưng
    0.44
     પરંતુ
    0.41
     mutta
    0.39
    했지만
    0.38
     მაგრამ
    0.38
     선보
    0.38
    0.37
    Act Density 0.195%

    No Known Activations