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

    Neuronpedia

    INDEX
    Explanations

    diagrams and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    سٹم
    1.85
     kraj
    1.79
    ो
    1.79
    UAGES
    1.78
    ्तीय
    1.78
     uncovering
    1.73
    uring
    1.72
     récentes
    1.70
    лно
    1.70
     kidding
    1.69
    POSITIVE LOGITS
    াল
    2.31
    ५
    2.28
    gluten
    2.15
    or
    2.15
     counterclaim
    2.09
    ant
    2.06
    stol
    2.03
     stup
    2.02
    al
    2.01
    ged
    2.01
    Act Density 0.000%

    No Known Activations