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

    Neuronpedia

    INDEX
    Explanations

    geographic locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idunt
    0.43
     instance
    0.40
    iniz
    0.39
    ゙
    0.39
    instance
    0.38
    uts
    0.38
    no
    0.37
     উল্লেখিত
    0.37
    incident
    0.37
    her
    0.36
    POSITIVE LOGITS
    াফ
    0.41
    정에
    0.35
     нередко
    0.35
    ந்தார்
    0.34
    صرية
    0.34
    ้อม
    0.34
     intricacies
    0.33
     coffers
    0.33
     ferries
    0.33
     hostels
    0.33
    Act Density 0.007%

    No Known Activations