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

    Neuronpedia

    INDEX
    Explanations

    process saving performance life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enzimas
    0.59
     ຫຼື
    0.55
    InfoPlist
    0.54
    RoutingModule
    0.52
    LFT
    0.52
    LabelTool
    0.50
    MinIntensity
    0.50
    рії
    0.49
    ้
    0.49
    Đáp
    0.48
    POSITIVE LOGITS
    d
    0.45
     in
    0.44
     the
    0.43
    t
    0.43
     it
    0.42
    美好
    0.41
      
    0.40
    ре
    0.40
     water
    0.40
     condition
    0.39
    Act Density 0.000%

    No Known Activations