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

    Neuronpedia

    INDEX
    Explanations

    concerns and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    牫
    0.23
    ivating
    0.23
    ographical
    0.23
    ルの
    0.22
    겠지만
    0.22
    atlantic
    0.22
     of
    0.22
    asting
    0.21
    Page
    0.21
    -)
    0.21
    POSITIVE LOGITS
     intensa
    0.28
     tại
    0.27
     ভুগ
    0.27
     famosos
    0.27
     және
    0.27
     extraordinaire
    0.27
     Klav
    0.27
     również
    0.26
     famosa
    0.26
     cũng
    0.26
    Act Density 1.114%

    No Known Activations