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

    Neuronpedia

    INDEX
    Explanations

    explanations and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Buyer
    0.47
    Ave
    0.45
    walt
    0.45
    ómetro
    0.44
    Cate
    0.44
    multipart
    0.43
    ización
    0.43
    ఎం
    0.43
    e
    0.43
     મોટા
    0.42
    POSITIVE LOGITS
     kritik
    0.47
     kone
    0.45
     liebe
    0.44
     konst
    0.43
     pikiran
    0.43
     listrik
    0.42
     elektrom
    0.42
     itu
    0.42
    iske
    0.42
     elekt
    0.41
    Act Density 0.000%

    No Known Activations