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

    Neuronpedia

    INDEX
    Explanations

    relationship with the person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    0.44
    我认为
    0.44
    мі
    0.43
     яке
    0.41
    Aprend
    0.40
     gdy
    0.40
    Upgrade
    0.39
    ʚ
    0.39
    ร
    0.39
    ному
    0.38
    POSITIVE LOGITS
     Saturday
    0.50
     dwindling
    0.48
     রোববার
    0.47
     paralys
    0.45
    今年は
    0.45
     receding
    0.44
    0
    0.44
     pandemic
    0.43
     நேற்று
    0.43
     Visits
    0.43
    Act Density 0.003%

    No Known Activations