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

    Neuronpedia

    INDEX
    Explanations

    Russia, instinctively, qualify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stabilit
    0.41
     چیر
    0.40
     neat
    0.40
     rum
    0.40
     سریع
    0.40
     stability
    0.39
     dever
    0.39
     sat
    0.38
    ดัง
    0.38
     foaf
    0.38
    POSITIVE LOGITS
    ണാ
    0.40
    othérapie
    0.40
    Callbacks
    0.39
    плуа
    0.39
     السيد
    0.39
    AUD
    0.38
     applies
    0.37
     evaluates
    0.37
    否
    0.37
    LR
    0.36
    Act Density 0.000%

    No Known Activations