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

    Neuronpedia

    INDEX
    Explanations

    names of peoples and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apps
    0.63
     satisfying
    0.63
     software
    0.62
     bottlenecks
    0.61
     NaOH
    0.60
     unstructured
    0.59
     a
    0.58
     onboarding
    0.58
     encaps
    0.57
     asympt
    0.56
    POSITIVE LOGITS
    ussians
    1.06
     quienes
    1.03
     dynasty
    1.01
     aristocracy
    1.01
    ussian
    0.99
     tribe
    0.96
     aristocratic
    0.95
    anians
    0.95
    ชาว
    0.94
    দিগের
    0.94
    Act Density 0.230%

    No Known Activations