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

    Neuronpedia

    INDEX
    Explanations

    remote learning and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    úl
    0.39
     हळ
    0.39
     sakta
    0.38
    neurs
    0.37
    นาะ
    0.37
     Slowly
    0.37
     жан
    0.37
    เศ
    0.36
     свободно
    0.36
    缚
    0.36
    POSITIVE LOGITS
     classes
    0.91
     remote
    0.90
     instruction
    0.88
    授業
    0.86
    remote
    0.84
     Remote
    0.84
     수업
    0.82
    Remote
    0.82
     learning
    0.81
    classes
    0.81
    Act Density 0.009%

    No Known Activations